diff options
Diffstat (limited to 'include/linux')
32 files changed, 709 insertions, 268 deletions
diff --git a/include/linux/arcfb.h b/include/linux/arcfb.h new file mode 100644 index 000000000000..721e7654daeb --- /dev/null +++ b/include/linux/arcfb.h @@ -0,0 +1,8 @@ +#ifndef __LINUX_ARCFB_H__ +#define __LINUX_ARCFB_H__ + +#define FBIO_WAITEVENT _IO('F', 0x88) +#define FBIO_GETCONTROL2 _IOR('F', 0x89, size_t) + +#endif + diff --git a/include/linux/auto_fs4.h b/include/linux/auto_fs4.h index a1657fb99516..9343c89d843c 100644 --- a/include/linux/auto_fs4.h +++ b/include/linux/auto_fs4.h @@ -23,7 +23,7 @@ #define AUTOFS_MIN_PROTO_VERSION 3 #define AUTOFS_MAX_PROTO_VERSION 4 -#define AUTOFS_PROTO_SUBVERSION 6 +#define AUTOFS_PROTO_SUBVERSION 7 /* Mask for expire behaviour */ #define AUTOFS_EXP_IMMEDIATE 1 diff --git a/include/linux/fb.h b/include/linux/fb.h index b468bf496547..bc24beeed971 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -524,11 +524,11 @@ struct fb_pixmap { u32 offset; /* current offset to buffer */ u32 buf_align; /* byte alignment of each bitmap */ u32 scan_align; /* alignment per scanline */ - u32 access_align; /* alignment per read/write */ + u32 access_align; /* alignment per read/write (bits) */ u32 flags; /* see FB_PIXMAP_* */ /* access methods */ - void (*outbuf)(struct fb_info *info, u8 *addr, u8 *src, unsigned int size); - u8 (*inbuf) (struct fb_info *info, u8 *addr); + void (*writeio)(struct fb_info *info, void __iomem *dst, void *src, unsigned int size); + void (*readio) (struct fb_info *info, void *dst, void __iomem *src, unsigned int size); }; @@ -816,18 +816,9 @@ extern int unregister_framebuffer(struct fb_info *fb_info); extern int fb_prepare_logo(struct fb_info *fb_info); extern int fb_show_logo(struct fb_info *fb_info); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -extern void fb_iomove_buf_unaligned(struct fb_info *info, struct fb_pixmap *buf, - u8 *dst, u32 d_pitch, u8 *src, u32 idx, +extern void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx, u32 height, u32 shift_high, u32 shift_low, u32 mod); -extern void fb_iomove_buf_aligned(struct fb_info *info, struct fb_pixmap *buf, - u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, - u32 height); -extern void fb_sysmove_buf_unaligned(struct fb_info *info, struct fb_pixmap *buf, - u8 *dst, u32 d_pitch, u8 *src, u32 idx, - u32 height, u32 shift_high, u32 shift_low, u32 mod); -extern void fb_sysmove_buf_aligned(struct fb_info *info, struct fb_pixmap *buf, - u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, - u32 height); +extern void fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, u32 height); extern void fb_set_suspend(struct fb_info *info, int state); extern int fb_get_color_depth(struct fb_var_screeninfo *var); extern int fb_get_options(char *name, char **option); diff --git a/include/linux/font.h b/include/linux/font.h index fc2d690c9d5f..8fc80a7d78ac 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -25,19 +25,23 @@ struct font_desc { #define VGA8x16_IDX 1 #define PEARL8x8_IDX 2 #define VGA6x11_IDX 3 -#define SUN8x16_IDX 4 -#define SUN12x22_IDX 5 -#define ACORN8x8_IDX 6 -#define MINI4x6_IDX 7 +#define FONT7x14_IDX 4 +#define FONT10x18_IDX 5 +#define SUN8x16_IDX 6 +#define SUN12x22_IDX 7 +#define ACORN8x8_IDX 8 +#define MINI4x6_IDX 9 extern struct font_desc font_vga_8x8, - font_vga_8x16, - font_pearl_8x8, - font_vga_6x11, - font_sun_8x16, - font_sun_12x22, - font_acorn_8x8, - font_mini_4x6; + font_vga_8x16, + font_pearl_8x8, + font_vga_6x11, + font_7x14, + font_10x18, + font_sun_8x16, + font_sun_12x22, + font_acorn_8x8, + font_mini_4x6; /* Find a font with a specific name */ diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index faaff4c64559..70f54af87b9f 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -51,6 +51,7 @@ struct gianfar_platform_data { /* board specific information */ u32 board_flags; + u32 phy_flags; u32 phyid; u32 interruptPHY; u8 mac_addr[6]; @@ -61,9 +62,14 @@ struct gianfar_platform_data { #define FSL_GIANFAR_DEV_HAS_COALESCE 0x00000002 #define FSL_GIANFAR_DEV_HAS_RMON 0x00000004 #define FSL_GIANFAR_DEV_HAS_MULTI_INTR 0x00000008 +#define FSL_GIANFAR_DEV_HAS_CSUM 0x00000010 +#define FSL_GIANFAR_DEV_HAS_VLAN 0x00000020 +#define FSL_GIANFAR_DEV_HAS_EXTENDED_HASH 0x00000040 +#define FSL_GIANFAR_DEV_HAS_PADDING 0x00000080 /* Flags in gianfar_platform_data */ -#define FSL_GIANFAR_BRD_HAS_PHY_INTR 0x00000001 /* if not set use a timer */ +#define FSL_GIANFAR_BRD_HAS_PHY_INTR 0x00000001 /* set or use a timer */ +#define FSL_GIANFAR_BRD_IS_REDUCED 0x00000002 /* Set if RGMII, RMII */ struct fsl_i2c_platform_data { /* device specific information */ diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h new file mode 100644 index 000000000000..7fd0576a4454 --- /dev/null +++ b/include/linux/genalloc.h @@ -0,0 +1,40 @@ +/* + * Basic general purpose allocator for managing special purpose memory + * not managed by the regular kmalloc/kfree interface. + * Uses for this includes on-device special memory, uncached memory + * etc. + * + * This code is based on the buddy allocator found in the sym53c8xx_2 + * driver, adapted for general purpose use. + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <linux/spinlock.h> + +#define ALLOC_MIN_SHIFT 5 /* 32 bytes minimum */ +/* + * Link between free memory chunks of a given size. + */ +struct gen_pool_link { + struct gen_pool_link *next; +}; + +/* + * Memory pool descriptor. + */ +struct gen_pool { + spinlock_t lock; + unsigned long (*get_new_chunk)(struct gen_pool *); + struct gen_pool *next; + struct gen_pool_link *h; + unsigned long private; + int max_chunk_shift; +}; + +unsigned long gen_pool_alloc(struct gen_pool *poolp, int size); +void gen_pool_free(struct gen_pool *mp, unsigned long ptr, int size); +struct gen_pool *gen_pool_create(int nr_chunks, int max_chunk_shift, + unsigned long (*fp)(struct gen_pool *), + unsigned long data); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index af7407e8cfc5..8d6bf608b199 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -39,6 +39,7 @@ struct vm_area_struct; #define __GFP_COMP 0x4000u /* Add compound page metadata */ #define __GFP_ZERO 0x8000u /* Return zeroed page on success */ #define __GFP_NOMEMALLOC 0x10000u /* Don't use emergency reserves */ +#define __GFP_NORECLAIM 0x20000u /* No realy zone reclaim during allocation */ #define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */ #define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1) @@ -47,7 +48,7 @@ struct vm_area_struct; #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \ __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \ __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \ - __GFP_NOMEMALLOC) + __GFP_NOMEMALLOC|__GFP_NORECLAIM) #define GFP_ATOMIC (__GFP_HIGH) #define GFP_NOIO (__GFP_WAIT) @@ -132,5 +133,10 @@ extern void FASTCALL(free_cold_page(struct page *page)); #define free_page(addr) free_pages((addr),0) void page_alloc_init(void); +#ifdef CONFIG_NUMA +void drain_remote_pages(void); +#else +static inline void drain_remote_pages(void) { }; +#endif #endif /* __LINUX_GFP_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6af1ae4a8211..f529d1442815 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -4,6 +4,7 @@ #ifdef CONFIG_HUGETLB_PAGE #include <linux/mempolicy.h> +#include <asm/tlbflush.h> struct ctl_table; @@ -22,12 +23,6 @@ int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); int is_hugepage_mem_enough(size_t); unsigned long hugetlb_total_pages(void); -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write); -int is_aligned_hugepage_range(unsigned long addr, unsigned long len); -int pmd_huge(pmd_t pmd); struct page *alloc_huge_page(void); void free_huge_page(struct page *); @@ -35,6 +30,17 @@ extern unsigned long max_huge_pages; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; +/* arch callbacks */ + +pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr); +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); +struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, + int write); +struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmd, int write); +int is_aligned_hugepage_range(unsigned long addr, unsigned long len); +int pmd_huge(pmd_t pmd); + #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \ @@ -48,6 +54,28 @@ extern int sysctl_hugetlb_shm_group; int prepare_hugepage_range(unsigned long addr, unsigned long len); #endif +#ifndef ARCH_HAS_SETCLEAR_HUGE_PTE +#define set_huge_pte_at(mm, addr, ptep, pte) set_pte_at(mm, addr, ptep, pte) +#define huge_ptep_get_and_clear(mm, addr, ptep) ptep_get_and_clear(mm, addr, ptep) +#else +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); +#endif + +#ifndef ARCH_HAS_HUGETLB_PREFAULT_HOOK +#define hugetlb_prefault_arch_hook(mm) do { } while (0) +#else +void hugetlb_prefault_arch_hook(struct mm_struct *mm); +#endif + +#ifndef ARCH_HAS_HUGETLB_CLEAN_STALE_PGTABLE +#define hugetlb_clean_stale_pgtable(pte) BUG() +#else +void hugetlb_clean_stale_pgtable(pte_t *pte); +#endif + #else /* !CONFIG_HUGETLB_PAGE */ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) diff --git a/include/linux/ioc4.h b/include/linux/ioc4.h new file mode 100644 index 000000000000..3dd18b785ebd --- /dev/null +++ b/include/linux/ioc4.h @@ -0,0 +1,179 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2005 Silicon Graphics, Inc. All Rights Reserved. + */ + +#ifndef _LINUX_IOC4_H +#define _LINUX_IOC4_H + +#include <linux/interrupt.h> + +/*************** + * Definitions * + ***************/ + +/* Miscellaneous values inherent to hardware */ + +#define IOC4_EXTINT_COUNT_DIVISOR 520 /* PCI clocks per COUNT tick */ + +/*********************************** + * Structures needed by subdrivers * + ***********************************/ + +/* This structure fully describes the IOC4 miscellaneous registers which + * appear at bar[0]+0x00000 through bar[0]+0x0005c. The corresponding + * PCI resource is managed by the main IOC4 driver because it contains + * registers of interest to many different IOC4 subdrivers. + */ +struct ioc4_misc_regs { + /* Miscellaneous IOC4 registers */ + union ioc4_pci_err_addr_l { + uint32_t raw; + struct { + uint32_t valid:1; /* Address captured */ + uint32_t master_id:4; /* Unit causing error + * 0/1: Serial port 0 TX/RX + * 2/3: Serial port 1 TX/RX + * 4/5: Serial port 2 TX/RX + * 6/7: Serial port 3 TX/RX + * 8: ATA/ATAPI + * 9-15: Undefined + */ + uint32_t mul_err:1; /* Multiple errors occurred */ + uint32_t addr:26; /* Bits 31-6 of error addr */ + } fields; + } pci_err_addr_l; + uint32_t pci_err_addr_h; /* Bits 63-32 of error addr */ + union ioc4_sio_int { + uint32_t raw; + struct { + uint8_t tx_mt:1; /* TX ring buffer empty */ + uint8_t rx_full:1; /* RX ring buffer full */ + uint8_t rx_high:1; /* RX high-water exceeded */ + uint8_t rx_timer:1; /* RX timer has triggered */ + uint8_t delta_dcd:1; /* DELTA_DCD seen */ + uint8_t delta_cts:1; /* DELTA_CTS seen */ + uint8_t intr_pass:1; /* Interrupt pass-through */ + uint8_t tx_explicit:1; /* TX, MCW, or delay complete */ + } fields[4]; + } sio_ir; /* Serial interrupt state */ + union ioc4_other_int { + uint32_t raw; + struct { + uint32_t ata_int:1; /* ATA port passthru */ + uint32_t ata_memerr:1; /* ATA halted by mem error */ + uint32_t memerr:4; /* Serial halted by mem err */ + uint32_t kbd_int:1; /* kbd/mouse intr asserted */ + uint32_t reserved:16; /* zero */ + uint32_t rt_int:1; /* INT_OUT section latch */ + uint32_t gen_int:8; /* Intr. from generic pins */ + } fields; + } other_ir; /* Other interrupt state */ + union ioc4_sio_int sio_ies; /* Serial interrupt enable set */ + union ioc4_other_int other_ies; /* Other interrupt enable set */ + union ioc4_sio_int sio_iec; /* Serial interrupt enable clear */ + union ioc4_other_int other_iec; /* Other interrupt enable clear */ + union ioc4_sio_cr { + uint32_t raw; + struct { + uint32_t cmd_pulse:4; /* Bytebus strobe width */ + uint32_t arb_diag:3; /* PCI bus requester */ + uint32_t sio_diag_idle:1; /* Active ser req? */ + uint32_t ata_diag_idle:1; /* Active ATA req? */ + uint32_t ata_diag_active:1; /* ATA req is winner */ + uint32_t reserved:22; /* zero */ + } fields; + } sio_cr; + uint32_t unused1; + union ioc4_int_out { + uint32_t raw; + struct { + uint32_t count:16; /* Period control */ + uint32_t mode:3; /* Output signal shape */ + uint32_t reserved:11; /* zero */ + uint32_t diag:1; /* Timebase control */ + uint32_t int_out:1; /* Current value */ + } fields; + } int_out; /* External interrupt output control */ + uint32_t unused2; + union ioc4_gpcr { + uint32_t raw; + struct { + uint32_t dir:8; /* Pin direction */ + uint32_t edge:8; /* Edge/level mode */ + uint32_t reserved1:4; /* zero */ + uint32_t int_out_en:1; /* INT_OUT enable */ + uint32_t reserved2:11; /* zero */ + } fields; + } gpcr_s; /* Generic PIO control set */ + union ioc4_gpcr gpcr_c; /* Generic PIO control clear */ + union ioc4_gpdr { + uint32_t raw; + struct { + uint32_t gen_pin:8; /* State of pins */ + uint32_t reserved:24; + } fields; + } gpdr; /* Generic PIO data */ + uint32_t unused3; + union ioc4_gppr { + uint32_t raw; + struct { + uint32_t gen_pin:1; /* Single pin state */ + uint32_t reserved:31; + } fields; + } gppr[8]; /* Generic PIO pins */ +}; + +/* Masks for GPCR DIR pins */ +#define IOC4_GPCR_DIR_0 0x01 /* External interrupt output */ +#define IOC4_GPCR_DIR_1 0x02 /* External interrupt input */ +#define IOC4_GPCR_DIR_2 0x04 +#define IOC4_GPCR_DIR_3 0x08 /* Keyboard/mouse presence */ +#define IOC4_GPCR_DIR_4 0x10 /* Ser. port 0 xcvr select (0=232, 1=422) */ +#define IOC4_GPCR_DIR_5 0x20 /* Ser. port 1 xcvr select (0=232, 1=422) */ +#define IOC4_GPCR_DIR_6 0x40 /* Ser. port 2 xcvr select (0=232, 1=422) */ +#define IOC4_GPCR_DIR_7 0x80 /* Ser. port 3 xcvr select (0=232, 1=422) */ + +/* Masks for GPCR EDGE pins */ +#define IOC4_GPCR_EDGE_0 0x01 +#define IOC4_GPCR_EDGE_1 0x02 /* External interrupt input */ +#define IOC4_GPCR_EDGE_2 0x04 +#define IOC4_GPCR_EDGE_3 0x08 +#define IOC4_GPCR_EDGE_4 0x10 +#define IOC4_GPCR_EDGE_5 0x20 +#define IOC4_GPCR_EDGE_6 0x40 +#define IOC4_GPCR_EDGE_7 0x80 + +/* One of these per IOC4 */ +struct ioc4_driver_data { + struct list_head idd_list; + unsigned long idd_bar0; + struct pci_dev *idd_pdev; + const struct pci_device_id *idd_pci_id; + struct __iomem ioc4_misc_regs *idd_misc_regs; + unsigned long count_period; + void *idd_serial_data; +}; + +/* One per submodule */ +struct ioc4_submodule { + struct list_head is_list; + char *is_name; + struct module *is_owner; + int (*is_probe) (struct ioc4_driver_data *); + int (*is_remove) (struct ioc4_driver_data *); +}; + +#define IOC4_NUM_CARDS 8 /* max cards per partition */ + +/********************************** + * Functions needed by submodules * + **********************************/ + +extern int ioc4_register_submodule(struct ioc4_submodule *); +extern void ioc4_unregister_submodule(struct ioc4_submodule *); + +#endif /* _LINUX_IOC4_H */ diff --git a/include/linux/ioc4_common.h b/include/linux/ioc4_common.h deleted file mode 100644 index b03bcc46df55..000000000000 --- a/include/linux/ioc4_common.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2005 Silicon Graphics, Inc. All Rights Reserved. - */ - -#ifndef _LINUX_IOC4_COMMON_H -#define _LINUX_IOC4_COMMON_H - -/* prototypes */ - -int ioc4_serial_init(void); - -int ioc4_serial_attach_one(struct pci_dev *pdev, const struct - pci_device_id *pci_id); -int ioc4_ide_attach_one(struct pci_dev *pdev, const struct - pci_device_id *pci_id); - -#endif /* _LINUX_IOC4_COMMON_H */ diff --git a/include/linux/irq.h b/include/linux/irq.h index c3ff4d101667..7fc1022be9ee 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -47,6 +47,10 @@ struct hw_interrupt_type { void (*ack)(unsigned int irq); void (*end)(unsigned int irq); void (*set_affinity)(unsigned int irq, cpumask_t dest); + /* Currently used only by UML, might disappear one day.*/ +#ifdef CONFIG_IRQ_RELEASE_METHOD + void (*release)(unsigned int irq, void *dev_id); +#endif }; typedef struct hw_interrupt_type hw_irq_controller; diff --git a/include/linux/mm.h b/include/linux/mm.h index 17518fe0b311..1813b162b0a8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -691,6 +691,12 @@ extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +#ifdef CONFIG_NUMA +extern void setup_per_cpu_pageset(void); +#else +static inline void setup_per_cpu_pageset(void) {} +#endif + /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e530c6c092f1..4733d35d8223 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -63,6 +63,12 @@ struct per_cpu_pageset { #endif } ____cacheline_aligned_in_smp; +#ifdef CONFIG_NUMA +#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)]) +#else +#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)]) +#endif + #define ZONE_DMA 0 #define ZONE_NORMAL 1 #define ZONE_HIGHMEM 2 @@ -122,8 +128,11 @@ struct zone { */ unsigned long lowmem_reserve[MAX_NR_ZONES]; +#ifdef CONFIG_NUMA + struct per_cpu_pageset *pageset[NR_CPUS]; +#else struct per_cpu_pageset pageset[NR_CPUS]; - +#endif /* * free areas of different sizes */ @@ -145,6 +154,14 @@ struct zone { int all_unreclaimable; /* All pages pinned */ /* + * Does the allocator try to reclaim pages from the zone as soon + * as it fails a watermark_ok() in __alloc_pages? + */ + int reclaim_pages; + /* A count of how many reclaimers are scanning this zone */ + atomic_t reclaim_in_progress; + + /* * prev_priority holds the scanning priority for this zone. It is * defined as the scanning priority at which we achieved our reclaim * target at the previous try_to_free_pages() or balance_pgdat() @@ -381,7 +398,7 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *, #include <linux/topology.h> /* Returns the number of the current Node. */ -#define numa_node_id() (cpu_to_node(_smp_processor_id())) +#define numa_node_id() (cpu_to_node(raw_smp_processor_id())) #ifndef CONFIG_DISCONTIGMEM diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 9e5750079e09..3ebc36afae1a 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -75,12 +75,6 @@ enum nf_ip_hook_priorities { #define SO_ORIGINAL_DST 80 #ifdef __KERNEL__ -#ifdef CONFIG_NETFILTER_DEBUG -void nf_debug_ip_local_deliver(struct sk_buff *skb); -void nf_debug_ip_loopback_xmit(struct sk_buff *newskb); -void nf_debug_ip_finish_output2(struct sk_buff *skb); -#endif /*CONFIG_NETFILTER_DEBUG*/ - extern int ip_route_me_harder(struct sk_buff **pskb); /* Call this before modifying an existing IP packet: ensures it is diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h index d84be02cb4fc..694aec9b4784 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_core.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h @@ -1,7 +1,6 @@ #ifndef _IP_CONNTRACK_CORE_H #define _IP_CONNTRACK_CORE_H #include <linux/netfilter.h> -#include <linux/netfilter_ipv4/lockhelp.h> /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use @@ -47,6 +46,6 @@ static inline int ip_conntrack_confirm(struct sk_buff **pskb) extern struct list_head *ip_conntrack_hash; extern struct list_head ip_conntrack_expect_list; -DECLARE_RWLOCK_EXTERN(ip_conntrack_lock); +extern rwlock_t ip_conntrack_lock; #endif /* _IP_CONNTRACK_CORE_H */ diff --git a/include/linux/netfilter_ipv4/ip_nat.h b/include/linux/netfilter_ipv4/ip_nat.h index 2b72b86176f0..e201ec6e9905 100644 --- a/include/linux/netfilter_ipv4/ip_nat.h +++ b/include/linux/netfilter_ipv4/ip_nat.h @@ -50,10 +50,9 @@ struct ip_nat_multi_range_compat #ifdef __KERNEL__ #include <linux/list.h> -#include <linux/netfilter_ipv4/lockhelp.h> /* Protects NAT hash tables, and NAT-private part of conntracks. */ -DECLARE_RWLOCK_EXTERN(ip_nat_lock); +extern rwlock_t ip_nat_lock; /* The structure embedded in the conntrack structure. */ struct ip_nat_info diff --git a/include/linux/netfilter_ipv4/listhelp.h b/include/linux/netfilter_ipv4/listhelp.h index f2ae7c5e57bb..360429f48737 100644 --- a/include/linux/netfilter_ipv4/listhelp.h +++ b/include/linux/netfilter_ipv4/listhelp.h @@ -2,7 +2,6 @@ #define _LISTHELP_H #include <linux/config.h> #include <linux/list.h> -#include <linux/netfilter_ipv4/lockhelp.h> /* Header to do more comprehensive job than linux/list.h; assume list is first entry in structure. */ diff --git a/include/linux/netfilter_ipv4/lockhelp.h b/include/linux/netfilter_ipv4/lockhelp.h deleted file mode 100644 index a3288633ab46..000000000000 --- a/include/linux/netfilter_ipv4/lockhelp.h +++ /dev/null @@ -1,129 +0,0 @@ -#ifndef _LOCKHELP_H -#define _LOCKHELP_H -#include <linux/config.h> - -#include <linux/spinlock.h> -#include <asm/atomic.h> -#include <linux/interrupt.h> -#include <linux/smp.h> - -/* Header to do help in lock debugging. */ - -#ifdef CONFIG_NETFILTER_DEBUG -struct spinlock_debug -{ - spinlock_t l; - atomic_t locked_by; -}; - -struct rwlock_debug -{ - rwlock_t l; - long read_locked_map; - long write_locked_map; -}; - -#define DECLARE_LOCK(l) \ -struct spinlock_debug l = { SPIN_LOCK_UNLOCKED, ATOMIC_INIT(-1) } -#define DECLARE_LOCK_EXTERN(l) \ -extern struct spinlock_debug l -#define DECLARE_RWLOCK(l) \ -struct rwlock_debug l = { RW_LOCK_UNLOCKED, 0, 0 } -#define DECLARE_RWLOCK_EXTERN(l) \ -extern struct rwlock_debug l - -#define MUST_BE_LOCKED(l) \ -do { if (atomic_read(&(l)->locked_by) != smp_processor_id()) \ - printk("ASSERT %s:%u %s unlocked\n", __FILE__, __LINE__, #l); \ -} while(0) - -#define MUST_BE_UNLOCKED(l) \ -do { if (atomic_read(&(l)->locked_by) == smp_processor_id()) \ - printk("ASSERT %s:%u %s locked\n", __FILE__, __LINE__, #l); \ -} while(0) - -/* Write locked OK as well. */ -#define MUST_BE_READ_LOCKED(l) \ -do { if (!((l)->read_locked_map & (1UL << smp_processor_id())) \ - && !((l)->write_locked_map & (1UL << smp_processor_id()))) \ - printk("ASSERT %s:%u %s not readlocked\n", __FILE__, __LINE__, #l); \ -} while(0) - -#define MUST_BE_WRITE_LOCKED(l) \ -do { if (!((l)->write_locked_map & (1UL << smp_processor_id()))) \ - printk("ASSERT %s:%u %s not writelocked\n", __FILE__, __LINE__, #l); \ -} while(0) - -#define MUST_BE_READ_WRITE_UNLOCKED(l) \ -do { if ((l)->read_locked_map & (1UL << smp_processor_id())) \ - printk("ASSERT %s:%u %s readlocked\n", __FILE__, __LINE__, #l); \ - else if ((l)->write_locked_map & (1UL << smp_processor_id())) \ - printk("ASSERT %s:%u %s writelocked\n", __FILE__, __LINE__, #l); \ -} while(0) - -#define LOCK_BH(lk) \ -do { \ - MUST_BE_UNLOCKED(lk); \ - spin_lock_bh(&(lk)->l); \ - atomic_set(&(lk)->locked_by, smp_processor_id()); \ -} while(0) - -#define UNLOCK_BH(lk) \ -do { \ - MUST_BE_LOCKED(lk); \ - atomic_set(&(lk)->locked_by, -1); \ - spin_unlock_bh(&(lk)->l); \ -} while(0) - -#define READ_LOCK(lk) \ -do { \ - MUST_BE_READ_WRITE_UNLOCKED(lk); \ - read_lock_bh(&(lk)->l); \ - set_bit(smp_processor_id(), &(lk)->read_locked_map); \ -} while(0) - -#define WRITE_LOCK(lk) \ -do { \ - MUST_BE_READ_WRITE_UNLOCKED(lk); \ - write_lock_bh(&(lk)->l); \ - set_bit(smp_processor_id(), &(lk)->write_locked_map); \ -} while(0) - -#define READ_UNLOCK(lk) \ -do { \ - if (!((lk)->read_locked_map & (1UL << smp_processor_id()))) \ - printk("ASSERT: %s:%u %s not readlocked\n", \ - __FILE__, __LINE__, #lk); \ - clear_bit(smp_processor_id(), &(lk)->read_locked_map); \ - read_unlock_bh(&(lk)->l); \ -} while(0) - -#define WRITE_UNLOCK(lk) \ -do { \ - MUST_BE_WRITE_LOCKED(lk); \ - clear_bit(smp_processor_id(), &(lk)->write_locked_map); \ - write_unlock_bh(&(lk)->l); \ -} while(0) - -#else -#define DECLARE_LOCK(l) spinlock_t l = SPIN_LOCK_UNLOCKED -#define DECLARE_LOCK_EXTERN(l) extern spinlock_t l -#define DECLARE_RWLOCK(l) rwlock_t l = RW_LOCK_UNLOCKED -#define DECLARE_RWLOCK_EXTERN(l) extern rwlock_t l - -#define MUST_BE_LOCKED(l) -#define MUST_BE_UNLOCKED(l) -#define MUST_BE_READ_LOCKED(l) -#define MUST_BE_WRITE_LOCKED(l) -#define MUST_BE_READ_WRITE_UNLOCKED(l) - -#define LOCK_BH(l) spin_lock_bh(l) -#define UNLOCK_BH(l) spin_unlock_bh(l) - -#define READ_LOCK(l) read_lock_bh(l) -#define WRITE_LOCK(l) write_lock_bh(l) -#define READ_UNLOCK(l) read_unlock_bh(l) -#define WRITE_UNLOCK(l) write_unlock_bh(l) -#endif /*CONFIG_NETFILTER_DEBUG*/ - -#endif /* _LOCKHELP_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 561d4dc75836..3029cad63a01 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -147,7 +147,7 @@ struct netlink_callback int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); int family; - long args[4]; + long args[5]; }; struct netlink_notify diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 39ab8c6b5652..f5a6695d4d21 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -61,21 +61,20 @@ #define PG_active 6 #define PG_slab 7 /* slab debug (Suparna wants this) */ -#define PG_highmem 8 -#define PG_checked 9 /* kill me in 2.5.<early>. */ -#define PG_arch_1 10 -#define PG_reserved 11 - -#define PG_private 12 /* Has something at ->private */ -#define PG_writeback 13 /* Page is under writeback */ -#define PG_nosave 14 /* Used for system suspend/resume */ -#define PG_compound 15 /* Part of a compound page */ - -#define PG_swapcache 16 /* Swap page: swp_entry_t in private */ -#define PG_mappedtodisk 17 /* Has blocks allocated on-disk */ -#define PG_reclaim 18 /* To be reclaimed asap */ -#define PG_nosave_free 19 /* Free, should not be written */ -#define PG_uncached 20 /* Page has been mapped as uncached */ +#define PG_checked 8 /* kill me in 2.5.<early>. */ +#define PG_arch_1 9 +#define PG_reserved 10 +#define PG_private 11 /* Has something at ->private */ + +#define PG_writeback 12 /* Page is under writeback */ +#define PG_nosave 13 /* Used for system suspend/resume */ +#define PG_compound 14 /* Part of a compound page */ +#define PG_swapcache 15 /* Swap page: swp_entry_t in private */ + +#define PG_mappedtodisk 16 /* Has blocks allocated on-disk */ +#define PG_reclaim 17 /* To be reclaimed asap */ +#define PG_nosave_free 18 /* Free, should not be written */ +#define PG_uncached 19 /* Page has been mapped as uncached */ /* * Global page accounting. One instance per CPU. Only unsigned longs are @@ -136,8 +135,8 @@ struct page_state { extern void get_page_state(struct page_state *ret); extern void get_full_page_state(struct page_state *ret); -extern unsigned long __read_page_state(unsigned offset); -extern void __mod_page_state(unsigned offset, unsigned long delta); +extern unsigned long __read_page_state(unsigned long offset); +extern void __mod_page_state(unsigned long offset, unsigned long delta); #define read_page_state(member) \ __read_page_state(offsetof(struct page_state, member)) @@ -215,7 +214,7 @@ extern void __mod_page_state(unsigned offset, unsigned long delta); #define TestSetPageSlab(page) test_and_set_bit(PG_slab, &(page)->flags) #ifdef CONFIG_HIGHMEM -#define PageHighMem(page) test_bit(PG_highmem, &(page)->flags) +#define PageHighMem(page) is_highmem(page_zone(page)) #else #define PageHighMem(page) 0 /* needed to optimize away at compile time */ #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0422031161ba..d9a25647a295 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -52,12 +52,12 @@ void release_pages(struct page **pages, int nr, int cold); static inline struct page *page_cache_alloc(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x), 0); + return alloc_pages(mapping_gfp_mask(x)|__GFP_NORECLAIM, 0); } static inline struct page *page_cache_alloc_cold(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); + return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD|__GFP_NORECLAIM, 0); } typedef int filler_t(void *, struct page *); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b8b4ebf9abf1..63e89e47b8e9 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -575,6 +575,7 @@ #define PCI_DEVICE_ID_CT_65550 0x00e0 #define PCI_DEVICE_ID_CT_65554 0x00e4 #define PCI_DEVICE_ID_CT_65555 0x00e5 +#define PCI_DEVICE_ID_CT_69000 0x00c0 #define PCI_VENDOR_ID_MIRO 0x1031 #define PCI_DEVICE_ID_MIRO_36050 0x5601 diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h new file mode 100644 index 000000000000..e24b74b11150 --- /dev/null +++ b/include/linux/raid/bitmap.h @@ -0,0 +1,273 @@ +/* + * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003 + * + * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc. + */ +#ifndef BITMAP_H +#define BITMAP_H 1 + +#define BITMAP_MAJOR 3 +#define BITMAP_MINOR 38 + +/* + * in-memory bitmap: + * + * Use 16 bit block counters to track pending writes to each "chunk". + * The 2 high order bits are special-purpose, the first is a flag indicating + * whether a resync is needed. The second is a flag indicating whether a + * resync is active. + * This means that the counter is actually 14 bits: + * + * +--------+--------+------------------------------------------------+ + * | resync | resync | counter | + * | needed | active | | + * | (0-1) | (0-1) | (0-16383) | + * +--------+--------+------------------------------------------------+ + * + * The "resync needed" bit is set when: + * a '1' bit is read from storage at startup. + * a write request fails on some drives + * a resync is aborted on a chunk with 'resync active' set + * It is cleared (and resync-active set) when a resync starts across all drives + * of the chunk. + * + * + * The "resync active" bit is set when: + * a resync is started on all drives, and resync_needed is set. + * resync_needed will be cleared (as long as resync_active wasn't already set). + * It is cleared when a resync completes. + * + * The counter counts pending write requests, plus the on-disk bit. + * When the counter is '1' and the resync bits are clear, the on-disk + * bit can be cleared aswell, thus setting the counter to 0. + * When we set a bit, or in the counter (to start a write), if the fields is + * 0, we first set the disk bit and set the counter to 1. + * + * If the counter is 0, the on-disk bit is clear and the stipe is clean + * Anything that dirties the stipe pushes the counter to 2 (at least) + * and sets the on-disk bit (lazily). + * If a periodic sweep find the counter at 2, it is decremented to 1. + * If the sweep find the counter at 1, the on-disk bit is cleared and the + * counter goes to zero. + * + * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block + * counters as a fallback when "page" memory cannot be allocated: + * + * Normal case (page memory allocated): + * + * page pointer (32-bit) + * + * [ ] ------+ + * | + * +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters) + * c1 c2 c2048 + * + * Hijacked case (page memory allocation failed): + * + * hijacked page pointer (32-bit) + * + * [ ][ ] (no page memory allocated) + * counter #1 (16-bit) counter #2 (16-bit) + * + */ + +#ifdef __KERNEL__ + +#define PAGE_BITS (PAGE_SIZE << 3) +#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3) + +typedef __u16 bitmap_counter_t; +#define COUNTER_BITS 16 +#define COUNTER_BIT_SHIFT 4 +#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8) +#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3) + +#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1))) +#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2))) +#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1) +#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK) +#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK) +#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX) + +/* how many counters per page? */ +#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS) +/* same, except a shift value for more efficient bitops */ +#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT) +/* same, except a mask value for more efficient bitops */ +#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1) + +#define BITMAP_BLOCK_SIZE 512 +#define BITMAP_BLOCK_SHIFT 9 + +/* how many blocks per chunk? (this is variable) */ +#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT) +#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT) +#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1) + +/* when hijacked, the counters and bits represent even larger "chunks" */ +/* there will be 1024 chunks represented by each counter in the page pointers */ +#define PAGEPTR_BLOCK_RATIO(bitmap) \ + (CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1) +#define PAGEPTR_BLOCK_SHIFT(bitmap) \ + (CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1) +#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1) + +/* + * on-disk bitmap: + * + * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap + * file a page at a time. There's a superblock at the start of the file. + */ + +/* map chunks (bits) to file pages - offset by the size of the superblock */ +#define CHUNK_BIT_OFFSET(chunk) ((chunk) + (sizeof(bitmap_super_t) << 3)) + +#endif + +/* + * bitmap structures: + */ + +#define BITMAP_MAGIC 0x6d746962 + +/* use these for bitmap->flags and bitmap->sb->state bit-fields */ +enum bitmap_state { + BITMAP_ACTIVE = 0x001, /* the bitmap is in use */ + BITMAP_STALE = 0x002 /* the bitmap file is out of date or had -EIO */ +}; + +/* the superblock at the front of the bitmap file -- little endian */ +typedef struct bitmap_super_s { + __u32 magic; /* 0 BITMAP_MAGIC */ + __u32 version; /* 4 the bitmap major for now, could change... */ + __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */ + __u64 events; /* 24 event counter for the bitmap (1)*/ + __u64 events_cleared;/*32 event counter when last bit cleared (2) */ + __u64 sync_size; /* 40 the size of the md device's sync range(3) */ + __u32 state; /* 48 bitmap state information */ + __u32 chunksize; /* 52 the bitmap chunk size in bytes */ + __u32 daemon_sleep; /* 56 seconds between disk flushes */ + + __u8 pad[256 - 60]; /* set to zero */ +} bitmap_super_t; + +/* notes: + * (1) This event counter is updated before the eventcounter in the md superblock + * When a bitmap is loaded, it is only accepted if this event counter is equal + * to, or one greater than, the event counter in the superblock. + * (2) This event counter is updated when the other one is *if*and*only*if* the + * array is not degraded. As bits are not cleared when the array is degraded, + * this represents the last time that any bits were cleared. + * If a device is being added that has an event count with this value or + * higher, it is accepted as conforming to the bitmap. + * (3)This is the number of sectors represented by the bitmap, and is the range that + * resync happens across. For raid1 and raid5/6 it is the size of individual + * devices. For raid10 it is the size of the array. + */ + +#ifdef __KERNEL__ + +/* the in-memory bitmap is represented by bitmap_pages */ +struct bitmap_page { + /* + * map points to the actual memory page + */ + char *map; + /* + * in emergencies (when map cannot be alloced), hijack the map + * pointer and use it as two counters itself + */ + unsigned int hijacked:1; + /* + * count of dirty bits on the page + */ + unsigned int count:31; +}; + +/* keep track of bitmap file pages that have pending writes on them */ +struct page_list { + struct list_head list; + struct page *page; +}; + +/* the main bitmap structure - one per mddev */ +struct bitmap { + struct bitmap_page *bp; + unsigned long pages; /* total number of pages in the bitmap */ + unsigned long missing_pages; /* number of pages not yet allocated */ + + mddev_t *mddev; /* the md device that the bitmap is for */ + + int counter_bits; /* how many bits per block counter */ + + /* bitmap chunksize -- how much data does each bit represent? */ + unsigned long chunksize; + unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */ + unsigned long chunks; /* total number of data chunks for the array */ + + /* We hold a count on the chunk currently being synced, and drop + * it when the last block is started. If the resync is aborted + * midway, we need to be able to drop that count, so we remember + * the counted chunk.. + */ + unsigned long syncchunk; + + __u64 events_cleared; + + /* bitmap spinlock */ + spinlock_t lock; + + long offset; /* offset from superblock if file is NULL */ + struct file *file; /* backing disk file */ + struct page *sb_page; /* cached copy of the bitmap file superblock */ + struct page **filemap; /* list of cache pages for the file */ + unsigned long *filemap_attr; /* attributes associated w/ filemap pages */ + unsigned long file_pages; /* number of pages in the file */ + + unsigned long flags; + + /* + * the bitmap daemon - periodically wakes up and sweeps the bitmap + * file, cleaning up bits and flushing out pages to disk as necessary + */ + unsigned long daemon_lastrun; /* jiffies of last run */ + unsigned long daemon_sleep; /* how many seconds between updates? */ + + /* + * bitmap_writeback_daemon waits for file-pages that have been written, + * as there is no way to get a call-back when a page write completes. + */ + mdk_thread_t *writeback_daemon; + spinlock_t write_lock; + wait_queue_head_t write_wait; + struct list_head complete_pages; + mempool_t *write_pool; +}; + +/* the bitmap API */ + +/* these are used only by md/bitmap */ +int bitmap_create(mddev_t *mddev); +void bitmap_destroy(mddev_t *mddev); +int bitmap_active(struct bitmap *bitmap); + +char *file_path(struct file *file, char *buf, int count); +void bitmap_print_sb(struct bitmap *bitmap); +int bitmap_update_sb(struct bitmap *bitmap); + +int bitmap_setallbits(struct bitmap *bitmap); +void bitmap_write_all(struct bitmap *bitmap); + +/* these are exported */ +int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors); +void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, + int success); +int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks); +void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted); +void bitmap_close_sync(struct bitmap *bitmap); + +int bitmap_unplug(struct bitmap *bitmap); +int bitmap_daemon_work(struct bitmap *bitmap); +#endif + +#endif diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index a6a67d102bfa..ffa316ce4dc8 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -60,7 +60,14 @@ */ #define MD_MAJOR_VERSION 0 #define MD_MINOR_VERSION 90 -#define MD_PATCHLEVEL_VERSION 1 +/* + * MD_PATCHLEVEL_VERSION indicates kernel functionality. + * >=1 means different superblock formats are selectable using SET_ARRAY_INFO + * and major_version/minor_version accordingly + * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT + * in the super status byte + */ +#define MD_PATCHLEVEL_VERSION 2 extern int register_md_personality (int p_num, mdk_personality_t *p); extern int unregister_md_personality (int p_num); @@ -69,7 +76,7 @@ extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev), extern void md_unregister_thread (mdk_thread_t *thread); extern void md_wakeup_thread(mdk_thread_t *thread); extern void md_check_recovery(mddev_t *mddev); -extern void md_write_start(mddev_t *mddev); +extern void md_write_start(mddev_t *mddev, struct bio *bi); extern void md_write_end(mddev_t *mddev); extern void md_handle_safemode(mddev_t *mddev); extern void md_done_sync(mddev_t *mddev, int blocks, int ok); @@ -78,6 +85,12 @@ extern void md_unplug_mddev(mddev_t *mddev); extern void md_print_devices (void); +extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, + sector_t sector, int size, struct page *page); +extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, + struct page *page, int rw); + + #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); } #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index c9a0d4013be7..8c14ba565a45 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -15,6 +15,9 @@ #ifndef _MD_K_H #define _MD_K_H +/* and dm-bio-list.h is not under include/linux because.... ??? */ +#include "../../../drivers/md/dm-bio-list.h" + #define MD_RESERVED 0UL #define LINEAR 1UL #define RAID0 2UL @@ -180,6 +183,10 @@ struct mdk_rdev_s int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ + int saved_raid_disk; /* role that device used to have in the + * array and could again if we did a partial + * resync from the bitmap + */ atomic_t nr_pending; /* number of pending requests. * only maintained for arrays that @@ -252,6 +259,11 @@ struct mddev_s atomic_t recovery_active; /* blocks scheduled, but not written */ wait_queue_head_t recovery_wait; sector_t recovery_cp; + + spinlock_t write_lock; + wait_queue_head_t sb_wait; /* for waiting on superblock updates */ + atomic_t pending_writes; /* number of active superblock writes */ + unsigned int safemode; /* if set, update "clean" superblock * when no writes pending. */ @@ -260,6 +272,13 @@ struct mddev_s atomic_t writes_pending; request_queue_t *queue; /* for plugging ... */ + struct bitmap *bitmap; /* the bitmap for the device */ + struct file *bitmap_file; /* the bitmap file */ + long bitmap_offset; /* offset from superblock of + * start of bitmap. May be + * negative, but not '0' + */ + struct list_head all_mddevs; }; @@ -291,7 +310,7 @@ struct mdk_personality_s int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev); int (*hot_remove_disk) (mddev_t *mddev, int number); int (*spare_active) (mddev_t *mddev); - int (*sync_request)(mddev_t *mddev, sector_t sector_nr, int go_faster); + sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster); int (*resize) (mddev_t *mddev, sector_t sectors); int (*reshape) (mddev_t *mddev, int raid_disks); int (*reconfig) (mddev_t *mddev, int layout, int chunk_size); @@ -334,6 +353,7 @@ typedef struct mdk_thread_s { unsigned long flags; struct completion *event; struct task_struct *tsk; + unsigned long timeout; const char *name; } mdk_thread_t; diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h index 8ba95d67329f..dc65cd435494 100644 --- a/include/linux/raid/md_p.h +++ b/include/linux/raid/md_p.h @@ -96,6 +96,7 @@ typedef struct mdp_device_descriptor_s { #define MD_SB_CLEAN 0 #define MD_SB_ERRORS 1 +#define MD_SB_BITMAP_PRESENT 8 /* bitmap may be present nearby */ typedef struct mdp_superblock_s { /* * Constant generic information @@ -184,7 +185,7 @@ struct mdp_superblock_1 { /* constant array information - 128 bytes */ __u32 magic; /* MD_SB_MAGIC: 0xa92b4efc - little endian */ __u32 major_version; /* 1 */ - __u32 feature_map; /* 0 for now */ + __u32 feature_map; /* bit 0 set if 'bitmap_offset' is meaningful */ __u32 pad0; /* always set to 0 when writing */ __u8 set_uuid[16]; /* user-space generated. */ @@ -197,7 +198,11 @@ struct mdp_superblock_1 { __u32 chunksize; /* in 512byte sectors */ __u32 raid_disks; - __u8 pad1[128-96]; /* set to 0 when written */ + __u32 bitmap_offset; /* sectors after start of superblock that bitmap starts + * NOTE: signed, so bitmap can be before superblock + * only meaningful of feature_map[0] is set. + */ + __u8 pad1[128-100]; /* set to 0 when written */ /* constant this-device information - 64 bytes */ __u64 data_offset; /* sector start of data, often 0 */ diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h index a2df5c2a42af..81da20ccec4d 100644 --- a/include/linux/raid/md_u.h +++ b/include/linux/raid/md_u.h @@ -23,6 +23,7 @@ #define GET_DISK_INFO _IOR (MD_MAJOR, 0x12, mdu_disk_info_t) #define PRINT_RAID_DEBUG _IO (MD_MAJOR, 0x13) #define RAID_AUTORUN _IO (MD_MAJOR, 0x14) +#define GET_BITMAP_FILE _IOR (MD_MAJOR, 0x15, mdu_bitmap_file_t) /* configuration */ #define CLEAR_ARRAY _IO (MD_MAJOR, 0x20) @@ -36,6 +37,7 @@ #define HOT_ADD_DISK _IO (MD_MAJOR, 0x28) #define SET_DISK_FAULTY _IO (MD_MAJOR, 0x29) #define HOT_GENERATE_ERROR _IO (MD_MAJOR, 0x2a) +#define SET_BITMAP_FILE _IOW (MD_MAJOR, 0x2b, int) /* usage */ #define RUN_ARRAY _IOW (MD_MAJOR, 0x30, mdu_param_t) @@ -106,6 +108,11 @@ typedef struct mdu_start_info_s { } mdu_start_info_t; +typedef struct mdu_bitmap_file_s +{ + char pathname[4096]; +} mdu_bitmap_file_t; + typedef struct mdu_param_s { int personality; /* 1,2,3,4 */ diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index abbfdd9afe1e..9d93cf12e890 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -36,12 +36,21 @@ struct r1_private_data_s { spinlock_t device_lock; struct list_head retry_list; + /* queue pending writes and submit them on unplug */ + struct bio_list pending_bio_list; + /* queue of writes that have been unplugged */ + struct bio_list flushing_bio_list; + /* for use when syncing mirrors: */ spinlock_t resync_lock; - int nr_pending; - int barrier; + int nr_pending; + int barrier; sector_t next_resync; + int fullsync; /* set to 1 if a full sync is needed, + * (fresh device added). + * Cleared when a sync completes. + */ wait_queue_head_t wait_idle; wait_queue_head_t wait_resume; @@ -85,14 +94,17 @@ struct r1bio_s { int read_disk; struct list_head retry_list; + struct bitmap_update *bitmap_update; /* * if the IO is in WRITE direction, then multiple bios are used. * We choose the number when they are allocated. */ struct bio *bios[0]; + /* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/ }; /* bits for r1bio.state */ #define R1BIO_Uptodate 0 #define R1BIO_IsSync 1 +#define R1BIO_Degraded 2 #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4dbb109022f3..b58afd97a180 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -201,8 +201,8 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -extern void arch_unmap_area(struct vm_area_struct *area); -extern void arch_unmap_area_topdown(struct vm_area_struct *area); +extern void arch_unmap_area(struct mm_struct *, unsigned long); +extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #define set_mm_counter(mm, member, value) (mm)->_##member = (value) #define get_mm_counter(mm, member) ((mm)->_##member) @@ -218,9 +218,10 @@ struct mm_struct { unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); - void (*unmap_area) (struct vm_area_struct *area); - unsigned long mmap_base; /* base of mmap area */ - unsigned long free_area_cache; /* first hole */ + void (*unmap_area) (struct mm_struct *mm, unsigned long addr); + unsigned long mmap_base; /* base of mmap area */ + unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ + unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cc04f5cd2286..d7c839a21842 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -193,7 +193,6 @@ struct skb_shared_info { * @nfcache: Cache info * @nfct: Associated connection, if any * @nfctinfo: Relationship of this skb to the connection - * @nf_debug: Netfilter debugging * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @private: Data which is private to the HIPPI implementation * @tc_index: Traffic control index @@ -264,9 +263,6 @@ struct sk_buff { __u32 nfcache; __u32 nfctinfo; struct nf_conntrack *nfct; -#ifdef CONFIG_NETFILTER_DEBUG - unsigned int nf_debug; -#endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif @@ -1219,15 +1215,6 @@ static inline void nf_reset(struct sk_buff *skb) { nf_conntrack_put(skb->nfct); skb->nfct = NULL; -#ifdef CONFIG_NETFILTER_DEBUG - skb->nf_debug = 0; -#endif -} -static inline void nf_reset_debug(struct sk_buff *skb) -{ -#ifdef CONFIG_NETFILTER_DEBUG - skb->nf_debug = 0; -#endif } #ifdef CONFIG_BRIDGE_NETFILTER diff --git a/include/linux/smp.h b/include/linux/smp.h index dcf1db3b35d3..9dfa3ee769ae 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -92,10 +92,7 @@ void smp_prepare_boot_cpu(void); /* * These macros fold the SMP functionality into a single CPU system */ - -#if !defined(__smp_processor_id) || !defined(CONFIG_PREEMPT) -# define smp_processor_id() 0 -#endif +#define raw_smp_processor_id() 0 #define hard_smp_processor_id() 0 #define smp_call_function(func,info,retry,wait) ({ 0; }) #define on_each_cpu(func,info,retry,wait) ({ func(info); 0; }) @@ -106,30 +103,25 @@ static inline void smp_send_reschedule(int cpu) { } #endif /* !SMP */ /* - * DEBUG_PREEMPT support: check whether smp_processor_id() is being - * used in a preemption-safe way. + * smp_processor_id(): get the current CPU ID. * - * An architecture has to enable this debugging code explicitly. - * It can do so by renaming the smp_processor_id() macro to - * __smp_processor_id(). This should only be done after some minimal - * testing, because usually there are a number of false positives - * that an architecture will trigger. + * if DEBUG_PREEMPT is enabled the we check whether it is + * used in a preemption-safe way. (smp_processor_id() is safe + * if it's used in a preemption-off critical section, or in + * a thread that is bound to the current CPU.) * - * To fix a false positive (i.e. smp_processor_id() use that the - * debugging code reports but which use for some reason is legal), - * change the smp_processor_id() reference to _smp_processor_id(), - * which is the nondebug variant. NOTE: don't use this to hack around - * real bugs. + * NOTE: raw_smp_processor_id() is for internal use only + * (smp_processor_id() is the preferred variant), but in rare + * instances it might also be used to turn off false positives + * (i.e. smp_processor_id() use that the debugging code reports but + * which use for some reason is legal). Don't use this to hack around + * the warning message, as your code might not work under PREEMPT. */ -#ifdef __smp_processor_id -# if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT) - extern unsigned int smp_processor_id(void); -# else -# define smp_processor_id() __smp_processor_id() -# endif -# define _smp_processor_id() __smp_processor_id() +#ifdef CONFIG_DEBUG_PREEMPT + extern unsigned int debug_smp_processor_id(void); +# define smp_processor_id() debug_smp_processor_id() #else -# define _smp_processor_id() smp_processor_id() +# define smp_processor_id() raw_smp_processor_id() #endif #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) diff --git a/include/linux/swap.h b/include/linux/swap.h index 3bbc41be9bd0..2343f999e6e1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -172,7 +172,8 @@ extern int rotate_reclaimable_page(struct page *page); extern void swap_setup(void); /* linux/mm/vmscan.c */ -extern int try_to_free_pages(struct zone **, unsigned int, unsigned int); +extern int try_to_free_pages(struct zone **, unsigned int); +extern int zone_reclaim(struct zone *, unsigned int, unsigned int); extern int shrink_all_memory(int); extern int vm_swappiness; |