diff options
Diffstat (limited to 'include/linux')
42 files changed, 852 insertions, 439 deletions
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 1dbe074f1c64..43b406def35f 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -46,6 +46,8 @@ * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) + * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap + * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz * bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to 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 @@ -121,6 +123,10 @@ extern void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, int bits); extern int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); +extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, + const unsigned long *relmap, int bits); +extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, + int sz, int bits); extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 4e4e340592fb..6a5dbdc8a7dc 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -101,6 +101,8 @@ extern void reserve_bootmem_node(pg_data_t *pgdat, extern void free_bootmem_node(pg_data_t *pgdat, unsigned long addr, unsigned long size); +extern void *alloc_bootmem_section(unsigned long size, + unsigned long section_nr); #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE #define alloc_bootmem_node(pgdat, x) \ diff --git a/include/linux/cache.h b/include/linux/cache.h index 4552504c0228..97e24881c4c6 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -60,4 +60,8 @@ #endif #endif +#ifndef CONFIG_ARCH_HAS_CACHE_LINE_SIZE +#define cache_line_size() L1_CACHE_BYTES +#endif + #endif /* __LINUX_CACHE_H */ diff --git a/include/linux/capability.h b/include/linux/capability.h index 7d50ff6d269f..eaab759b1460 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -155,6 +155,7 @@ typedef struct kernel_cap_struct { * Add any capability from current's capability bounding set * to the current process' inheritable set * Allow taking bits out of capability bounding set + * Allow modification of the securebits for a process */ #define CAP_SETPCAP 8 @@ -490,8 +491,6 @@ extern const kernel_cap_t __cap_init_eff_set; int capable(int cap); int __capable(struct task_struct *t, int cap); -extern long cap_prctl_drop(unsigned long cap); - #endif /* __KERNEL__ */ #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 259c8051155d..9650806fe2ea 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -14,6 +14,8 @@ * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c * For details of cpus_remap(), see bitmap_remap in lib/bitmap.c. + * For details of cpus_onto(), see bitmap_onto in lib/bitmap.c. + * For details of cpus_fold(), see bitmap_fold in lib/bitmap.c. * * The available cpumask operations are: * @@ -53,7 +55,9 @@ * 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) - * int cpus_remap(dst, src, old, new) *dst = map(old, new)(src) + * void cpus_remap(dst, src, old, new) *dst = map(old, new)(src) + * void cpus_onto(dst, orig, relmap) *dst = orig relative to relmap + * void cpus_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_cpu_mask(cpu, mask) for-loop cpu over mask * @@ -330,6 +334,22 @@ static inline void __cpus_remap(cpumask_t *dstp, const cpumask_t *srcp, bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } +#define cpus_onto(dst, orig, relmap) \ + __cpus_onto(&(dst), &(orig), &(relmap), NR_CPUS) +static inline void __cpus_onto(cpumask_t *dstp, const cpumask_t *origp, + const cpumask_t *relmapp, int nbits) +{ + bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); +} + +#define cpus_fold(dst, orig, sz) \ + __cpus_fold(&(dst), &(orig), sz, NR_CPUS) +static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp, + int sz, int nbits) +{ + bitmap_fold(dstp->bits, origp->bits, sz, nbits); +} + #if NR_CPUS > 1 #define for_each_cpu_mask(cpu, mask) \ for ((cpu) = first_cpu(mask); \ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 726761e24003..038578362b47 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -26,7 +26,7 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); void cpuset_update_task_memory_state(void); -int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl); +int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask); extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask); @@ -103,7 +103,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) static inline void cpuset_init_current_mems_allowed(void) {} static inline void cpuset_update_task_memory_state(void) {} -static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) +static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 325acdf5c462..2a063b64133f 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -90,6 +90,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0; static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } +static inline void dmi_scan_machine(void) { return; } static inline int dmi_get_year(int year) { return 0; } static inline int dmi_name_in_vendors(const char *s) { return 0; } #define dmi_available 0 diff --git a/include/linux/fb.h b/include/linux/fb.h index 58c57a33e5dd..72295b099228 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -791,6 +791,17 @@ struct fb_tile_ops { */ #define FBINFO_MISC_ALWAYS_SETPAR 0x40000 +/* + * Host and GPU endianness differ. + */ +#define FBINFO_FOREIGN_ENDIAN 0x100000 +/* + * Big endian math. This is the same flags as above, but with different + * meaning, it is set by the fb subsystem depending FOREIGN_ENDIAN flag + * and host endianness. Drivers should not use this flag. + */ +#define FBINFO_BE_MATH 0x100000 + struct fb_info { int node; int flags; @@ -899,15 +910,11 @@ struct fb_info { #endif -#if defined (__BIG_ENDIAN) -#define FB_LEFT_POS(bpp) (32 - bpp) -#define FB_SHIFT_HIGH(val, bits) ((val) >> (bits)) -#define FB_SHIFT_LOW(val, bits) ((val) << (bits)) -#else -#define FB_LEFT_POS(bpp) (0) -#define FB_SHIFT_HIGH(val, bits) ((val) << (bits)) -#define FB_SHIFT_LOW(val, bits) ((val) >> (bits)) -#endif +#define FB_LEFT_POS(p, bpp) (fb_be_math(p) ? (32 - (bpp)) : 0) +#define FB_SHIFT_HIGH(p, val, bits) (fb_be_math(p) ? (val) >> (bits) : \ + (val) << (bits)) +#define FB_SHIFT_LOW(p, val, bits) (fb_be_math(p) ? (val) << (bits) : \ + (val) >> (bits)) /* * `Generic' versions of the frame buffer device operations @@ -970,6 +977,25 @@ extern void fb_deferred_io_cleanup(struct fb_info *info); extern int fb_deferred_io_fsync(struct file *file, struct dentry *dentry, int datasync); +static inline bool fb_be_math(struct fb_info *info) +{ +#ifdef CONFIG_FB_FOREIGN_ENDIAN +#if defined(CONFIG_FB_BOTH_ENDIAN) + return info->flags & FBINFO_BE_MATH; +#elif defined(CONFIG_FB_BIG_ENDIAN) + return true; +#elif defined(CONFIG_FB_LITTLE_ENDIAN) + return false; +#endif /* CONFIG_FB_BOTH_ENDIAN */ +#else +#ifdef __BIG_ENDIAN + return true; +#else + return false; +#endif /* __BIG_ENDIAN */ +#endif /* CONFIG_FB_FOREIGN_ENDIAN */ +} + /* drivers/video/fbsysfs.c */ extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev); extern void framebuffer_release(struct fb_info *info); diff --git a/include/linux/fs.h b/include/linux/fs.h index d6d7c52055c6..2c925747bc49 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -474,8 +474,8 @@ struct address_space_operations { int (*releasepage) (struct page *, gfp_t); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); - struct page* (*get_xip_page)(struct address_space *, sector_t, - int); + int (*get_xip_mem)(struct address_space *, pgoff_t, int, + void **, unsigned long *); /* migrate the contents of a page to the specified target */ int (*migratepage) (struct address_space *, struct page *, struct page *); @@ -1178,7 +1178,8 @@ struct block_device_operations { int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long); long (*unlocked_ioctl) (struct file *, unsigned, unsigned long); long (*compat_ioctl) (struct file *, unsigned, unsigned long); - int (*direct_access) (struct block_device *, sector_t, unsigned long *); + int (*direct_access) (struct block_device *, sector_t, + void **, unsigned long *); int (*media_changed) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 164be9da3c1b..c37653b6843f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -119,35 +119,22 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) static inline enum zone_type gfp_zone(gfp_t flags) { - int base = 0; - -#ifdef CONFIG_NUMA - if (flags & __GFP_THISNODE) - base = MAX_NR_ZONES; -#endif - #ifdef CONFIG_ZONE_DMA if (flags & __GFP_DMA) - return base + ZONE_DMA; + return ZONE_DMA; #endif #ifdef CONFIG_ZONE_DMA32 if (flags & __GFP_DMA32) - return base + ZONE_DMA32; + return ZONE_DMA32; #endif if ((flags & (__GFP_HIGHMEM | __GFP_MOVABLE)) == (__GFP_HIGHMEM | __GFP_MOVABLE)) - return base + ZONE_MOVABLE; + return ZONE_MOVABLE; #ifdef CONFIG_HIGHMEM if (flags & __GFP_HIGHMEM) - return base + ZONE_HIGHMEM; + return ZONE_HIGHMEM; #endif - return base + ZONE_NORMAL; -} - -static inline gfp_t set_migrateflags(gfp_t gfp, gfp_t migrate_flags) -{ - BUG_ON((gfp & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); - return (gfp & ~(GFP_MOVABLE_MASK)) | migrate_flags; + return ZONE_NORMAL; } /* @@ -157,13 +144,27 @@ static inline gfp_t set_migrateflags(gfp_t gfp, gfp_t migrate_flags) * virtual kernel addresses to the allocated page(s). */ +static inline int gfp_zonelist(gfp_t flags) +{ + if (NUMA_BUILD && unlikely(flags & __GFP_THISNODE)) + return 1; + + return 0; +} + /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. + * There are two zonelists per node, one for all zones with memory and + * one containing just zones from the node the zonelist belongs to. * * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets * optimized to &contig_page_data at compile-time. */ +static inline struct zonelist *node_zonelist(int nid, gfp_t flags) +{ + return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); +} #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } @@ -174,6 +175,10 @@ static inline void arch_alloc_page(struct page *page, int order) { } extern struct page *__alloc_pages(gfp_t, unsigned int, struct zonelist *); +extern struct page * +__alloc_pages_nodemask(gfp_t, unsigned int, + struct zonelist *, nodemask_t *nodemask); + static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { @@ -184,8 +189,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, if (nid < 0) nid = numa_node_id(); - return __alloc_pages(gfp_mask, order, - NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_mask)); + return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); } #ifdef CONFIG_NUMA diff --git a/include/linux/hid.h b/include/linux/hid.h index d951ec411241..4ce3b7a979ba 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -498,13 +498,13 @@ struct hid_parser { struct hid_class_descriptor { __u8 bDescriptorType; - __u16 wDescriptorLength; + __le16 wDescriptorLength; } __attribute__ ((packed)); struct hid_descriptor { __u8 bLength; __u8 bDescriptorType; - __u16 bcdHID; + __le16 bcdHID; __u8 bCountryCode; __u8 bNumDescriptors; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index addca4cd4f11..a79e80b689d8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -8,6 +8,7 @@ #include <linux/mempolicy.h> #include <linux/shm.h> #include <asm/tlbflush.h> +#include <asm/hugetlb.h> struct ctl_table; @@ -51,51 +52,6 @@ int pmd_huge(pmd_t pmd); void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); -#ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE -#define is_hugepage_only_range(mm, addr, len) 0 -#endif - -#ifndef ARCH_HAS_HUGETLB_FREE_PGD_RANGE -#define hugetlb_free_pgd_range free_pgd_range -#else -void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, - unsigned long end, unsigned long floor, - unsigned long ceiling); -#endif - -#ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE -/* - * If the arch doesn't supply something else, assume that hugepage - * size aligned regions are ok without further preparation. - */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) -{ - if (len & ~HPAGE_MASK) - return -EINVAL; - if (addr & ~HPAGE_MASK) - return -EINVAL; - return 0; -} -#else -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 - #else /* !CONFIG_HUGETLB_PAGE */ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) diff --git a/include/linux/i2o.h b/include/linux/i2o.h index e92170dda245..f65e58a1d925 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -613,14 +613,9 @@ struct i2o_sys_tbl { extern struct list_head i2o_controllers; /* Message functions */ -static inline struct i2o_message *i2o_msg_get(struct i2o_controller *); extern struct i2o_message *i2o_msg_get_wait(struct i2o_controller *, int); -static inline void i2o_msg_post(struct i2o_controller *, struct i2o_message *); -static inline int i2o_msg_post_wait(struct i2o_controller *, - struct i2o_message *, unsigned long); extern int i2o_msg_post_wait_mem(struct i2o_controller *, struct i2o_message *, unsigned long, struct i2o_dma *); -static inline void i2o_flush_reply(struct i2o_controller *, u32); /* IOP functions */ extern int i2o_status_get(struct i2o_controller *); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 37a6f5bc4a92..bf6b8a61f8db 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -9,6 +9,7 @@ #include <linux/ipc.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> +#include <linux/securebits.h> #include <net/net_namespace.h> #define INIT_FDTABLE \ @@ -172,7 +173,7 @@ extern struct group_info init_groups; .cap_inheritable = CAP_INIT_INH_SET, \ .cap_permitted = CAP_FULL_SET, \ .cap_bset = CAP_INIT_BSET, \ - .keep_capabilities = 0, \ + .securebits = SECUREBITS_DEFAULT, \ .user = INIT_USER, \ .comm = "swapper", \ .thread = INIT_THREAD, \ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0f28486f6360..1036631ff4fa 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -173,6 +173,13 @@ struct kretprobe_blackpoint { const char *name; void *addr; }; + +struct kprobe_blackpoint { + const char *name; + unsigned long start_addr; + unsigned long range; +}; + extern struct kretprobe_blackpoint kretprobe_blacklist[]; static inline void kretprobe_assert(struct kretprobe_instance *ri, @@ -227,15 +234,21 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); +int register_kprobes(struct kprobe **kps, int num); +void unregister_kprobes(struct kprobe **kps, int num); int setjmp_pre_handler(struct kprobe *, struct pt_regs *); int longjmp_break_handler(struct kprobe *, struct pt_regs *); int register_jprobe(struct jprobe *p); void unregister_jprobe(struct jprobe *p); +int register_jprobes(struct jprobe **jps, int num); +void unregister_jprobes(struct jprobe **jps, int num); void jprobe_return(void); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); void unregister_kretprobe(struct kretprobe *rp); +int register_kretprobes(struct kretprobe **rps, int num); +void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); @@ -254,16 +267,30 @@ static inline int register_kprobe(struct kprobe *p) { return -ENOSYS; } +static inline int register_kprobes(struct kprobe **kps, int num) +{ + return -ENOSYS; +} static inline void unregister_kprobe(struct kprobe *p) { } +static inline void unregister_kprobes(struct kprobe **kps, int num) +{ +} static inline int register_jprobe(struct jprobe *p) { return -ENOSYS; } +static inline int register_jprobes(struct jprobe **jps, int num) +{ + return -ENOSYS; +} static inline void unregister_jprobe(struct jprobe *p) { } +static inline void unregister_jprobes(struct jprobe **jps, int num) +{ +} static inline void jprobe_return(void) { } @@ -271,9 +298,16 @@ static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } +static inline int register_kretprobes(struct kretprobe **rps, int num) +{ + return -ENOSYS; +} static inline void unregister_kretprobe(struct kretprobe *rp) { } +static inline void unregister_kretprobes(struct kretprobe **rps, int num) +{ +} static inline void kprobe_flush_task(struct task_struct *tk) { } diff --git a/include/linux/list.h b/include/linux/list.h index dac16f99c701..b4a939b6b625 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -319,6 +319,15 @@ static inline int list_empty_careful(const struct list_head *head) return (next == head) && (next == head->prev); } +/** + * list_is_singular - tests whether a list has just one entry. + * @head: the list to test. + */ +static inline int list_is_singular(const struct list_head *head) +{ + return !list_empty(head) && (head->next == head->prev); +} + static inline void __list_splice(struct list_head *list, struct list_head *head) { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 8fee7a45736b..73e358612eaf 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -8,8 +8,18 @@ struct page; struct zone; struct pglist_data; +struct mem_section; #ifdef CONFIG_MEMORY_HOTPLUG + +/* + * Magic number for free bootmem. + * The normal smallest mapcount is -1. Here is smaller value than it. + */ +#define SECTION_INFO 0xfffffffe +#define MIX_INFO 0xfffffffd +#define NODE_INFO 0xfffffffc + /* * pgdat resizing functions */ @@ -64,9 +74,11 @@ extern int offline_pages(unsigned long, unsigned long, unsigned long); /* reasonably generic interface to expand the physical pages in a zone */ extern int __add_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); +extern int __remove_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages); /* - * Walk thorugh all memory which is registered as resource. + * Walk through all memory which is registered as resource. * arg is (start_pfn, nr_pages, private_arg_pointer) */ extern int walk_memory_resource(unsigned long start_pfn, @@ -142,6 +154,18 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) +{ +} +static inline void put_page_bootmem(struct page *page) +{ +} +#else +extern void register_page_bootmem_info_node(struct pglist_data *pgdat); +extern void put_page_bootmem(struct page *page); +#endif + #else /* ! CONFIG_MEMORY_HOTPLUG */ /* * Stub functions for when hotplug is off @@ -169,6 +193,10 @@ static inline int mhp_notimplemented(const char *func) return -ENOSYS; } +static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) +{ +} + #endif /* ! CONFIG_MEMORY_HOTPLUG */ extern int add_memory(int nid, u64 start, u64 size); @@ -176,5 +204,8 @@ extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); +extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); +extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, + unsigned long pnum); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 59c4865bc85f..3a39570b81b8 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -8,15 +8,32 @@ * Copyright 2003,2004 Andi Kleen SuSE Labs */ +/* + * Both the MPOL_* mempolicy mode and the MPOL_F_* optional mode flags are + * passed by the user to either set_mempolicy() or mbind() in an 'int' actual. + * The MPOL_MODE_FLAGS macro determines the legal set of optional mode flags. + */ + /* Policies */ -#define MPOL_DEFAULT 0 -#define MPOL_PREFERRED 1 -#define MPOL_BIND 2 -#define MPOL_INTERLEAVE 3 +enum { + MPOL_DEFAULT, + MPOL_PREFERRED, + MPOL_BIND, + MPOL_INTERLEAVE, + MPOL_MAX, /* always last member of enum */ +}; -#define MPOL_MAX MPOL_INTERLEAVE +/* Flags for set_mempolicy */ +#define MPOL_F_STATIC_NODES (1 << 15) +#define MPOL_F_RELATIVE_NODES (1 << 14) -/* Flags for get_mem_policy */ +/* + * MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to + * either set_mempolicy() or mbind(). + */ +#define MPOL_MODE_FLAGS (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) + +/* Flags for get_mempolicy */ #define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */ #define MPOL_F_ADDR (1<<1) /* look up vma using address */ #define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */ @@ -27,6 +44,14 @@ #define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to mapping */ #define MPOL_MF_INTERNAL (1<<3) /* Internal flags start here */ +/* + * Internal flags that share the struct mempolicy flags word with + * "mode flags". These flags are allocated from bit 0 up, as they + * are never OR'ed into the mode in mempolicy API arguments. + */ +#define MPOL_F_SHARED (1 << 0) /* identify shared policies */ +#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */ + #ifdef __KERNEL__ #include <linux/mmzone.h> @@ -35,7 +60,6 @@ #include <linux/spinlock.h> #include <linux/nodemask.h> -struct vm_area_struct; struct mm_struct; #ifdef CONFIG_NUMA @@ -54,22 +78,27 @@ struct mm_struct; * mmap_sem. * * Freeing policy: - * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd. - * All other policies don't have any external state. mpol_free() handles this. + * Mempolicy objects are reference counted. A mempolicy will be freed when + * mpol_put() decrements the reference count to zero. * - * Copying policy objects: - * For MPOL_BIND the zonelist must be always duplicated. mpol_clone() does this. + * Duplicating policy objects: + * mpol_dup() allocates a new mempolicy and copies the specified mempolicy + * to the new storage. The reference count of the new object is initialized + * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; - short policy; /* See MPOL_* above */ + unsigned short mode; /* See MPOL_* above */ + unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ union { - struct zonelist *zonelist; /* bind */ short preferred_node; /* preferred */ - nodemask_t nodes; /* interleave */ + nodemask_t nodes; /* interleave/bind */ /* undefined for default */ } v; - nodemask_t cpuset_mems_allowed; /* mempolicy relative to these nodes */ + union { + nodemask_t cpuset_mems_allowed; /* relative to these nodes */ + nodemask_t user_nodemask; /* nodemask passed by user */ + } w; }; /* @@ -77,18 +106,43 @@ struct mempolicy { * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ -extern void __mpol_free(struct mempolicy *pol); -static inline void mpol_free(struct mempolicy *pol) +extern void __mpol_put(struct mempolicy *pol); +static inline void mpol_put(struct mempolicy *pol) { if (pol) - __mpol_free(pol); + __mpol_put(pol); } -extern struct mempolicy *__mpol_copy(struct mempolicy *pol); -static inline struct mempolicy *mpol_copy(struct mempolicy *pol) +/* + * Does mempolicy pol need explicit unref after use? + * Currently only needed for shared policies. + */ +static inline int mpol_needs_cond_ref(struct mempolicy *pol) +{ + return (pol && (pol->flags & MPOL_F_SHARED)); +} + +static inline void mpol_cond_put(struct mempolicy *pol) +{ + if (mpol_needs_cond_ref(pol)) + __mpol_put(pol); +} + +extern struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol, + struct mempolicy *frompol); +static inline struct mempolicy *mpol_cond_copy(struct mempolicy *tompol, + struct mempolicy *frompol) +{ + if (!frompol) + return frompol; + return __mpol_cond_copy(tompol, frompol); +} + +extern struct mempolicy *__mpol_dup(struct mempolicy *pol); +static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) - pol = __mpol_copy(pol); + pol = __mpol_dup(pol); return pol; } @@ -108,11 +162,6 @@ static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b) return 1; return __mpol_equal(a, b); } -#define vma_mpol_equal(a,b) mpol_equal(vma_policy(a), vma_policy(b)) - -/* Could later add inheritance of the process policy here. */ - -#define mpol_set_vma_default(vma) ((vma)->vm_policy = NULL) /* * Tree of shared policies for a shared memory region. @@ -133,8 +182,7 @@ struct shared_policy { spinlock_t lock; }; -void mpol_shared_policy_init(struct shared_policy *info, int policy, - nodemask_t *nodes); +void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *new); @@ -149,9 +197,9 @@ extern void mpol_rebind_task(struct task_struct *tsk, extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern void mpol_fix_fork_child_flag(struct task_struct *p); -extern struct mempolicy default_policy; extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, - unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol); + unsigned long addr, gfp_t gfp_flags, + struct mempolicy **mpol, nodemask_t **nodemask); extern unsigned slab_node(struct mempolicy *policy); extern enum zone_type policy_zone; @@ -165,6 +213,13 @@ static inline void check_highest_zone(enum zone_type k) int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags); + +#ifdef CONFIG_TMPFS +extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context); + +extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, + int no_context); +#endif #else struct mempolicy {}; @@ -173,19 +228,26 @@ static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b) { return 1; } -#define vma_mpol_equal(a,b) 1 -#define mpol_set_vma_default(vma) do {} while(0) +static inline void mpol_put(struct mempolicy *p) +{ +} + +static inline void mpol_cond_put(struct mempolicy *pol) +{ +} -static inline void mpol_free(struct mempolicy *p) +static inline struct mempolicy *mpol_cond_copy(struct mempolicy *to, + struct mempolicy *from) { + return from; } static inline void mpol_get(struct mempolicy *pol) { } -static inline struct mempolicy *mpol_copy(struct mempolicy *old) +static inline struct mempolicy *mpol_dup(struct mempolicy *old) { return NULL; } @@ -199,8 +261,8 @@ static inline int mpol_set_shared_policy(struct shared_policy *info, return -EINVAL; } -static inline void mpol_shared_policy_init(struct shared_policy *info, - int policy, nodemask_t *nodes) +static inline void mpol_shared_policy_init(struct shared_policy *sp, + struct mempolicy *mpol) { } @@ -239,9 +301,12 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p) } static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, - unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol) + unsigned long addr, gfp_t gfp_flags, + struct mempolicy **mpol, nodemask_t **nodemask) { - return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags); + *mpol = NULL; + *nodemask = NULL; + return node_zonelist(0, gfp_flags); } static inline int do_migrate_pages(struct mm_struct *mm, @@ -254,6 +319,21 @@ static inline int do_migrate_pages(struct mm_struct *mm, static inline void check_highest_zone(int k) { } + +#ifdef CONFIG_TMPFS +static inline int mpol_parse_str(char *str, struct mempolicy **mpol, + int no_context) +{ + return 1; /* error */ +} + +static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, + int no_context) +{ + return 0; +} +#endif + #endif /* CONFIG_NUMA */ #endif /* __KERNEL__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 286d31521605..8b7f4a5d4f6a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -107,6 +107,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ #define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ +#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS @@ -164,8 +165,6 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); - struct page *(*nopage)(struct vm_area_struct *area, - unsigned long address, int *type); unsigned long (*nopfn)(struct vm_area_struct *area, unsigned long address); @@ -173,7 +172,25 @@ struct vm_operations_struct { * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); #ifdef CONFIG_NUMA + /* + * set_policy() op must add a reference to any non-NULL @new mempolicy + * to hold the policy upon return. Caller should pass NULL @new to + * remove a policy and fall back to surrounding context--i.e. do not + * install a MPOL_DEFAULT policy, nor the task or system default + * mempolicy. + */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); + + /* + * get_policy() op must add reference [mpol_get()] to any policy at + * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure + * in mm/mempolicy.c will do this automatically. + * get_policy() must NOT add a ref if the policy at (vma,addr) is not + * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. + * If no [shared/vma] mempolicy exists at the addr, get_policy() op + * must return NULL--i.e., do not "fallback" to task or system default + * policy. + */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from, @@ -397,11 +414,11 @@ static inline void set_compound_order(struct page *page, unsigned long order) * we have run out of space and have to fall back to an * alternate (slower) way of determining the node. * - * No sparsemem: | NODE | ZONE | ... | FLAGS | - * with space for node: | SECTION | NODE | ZONE | ... | FLAGS | - * no space for node: | SECTION | ZONE | ... | FLAGS | + * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | + * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | */ -#ifdef CONFIG_SPARSEMEM +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTIONS_WIDTH SECTIONS_SHIFT #else #define SECTIONS_WIDTH 0 @@ -409,9 +426,12 @@ static inline void set_compound_order(struct page *page, unsigned long order) #define ZONES_WIDTH ZONES_SHIFT -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= FLAGS_RESERVED +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS #define NODES_WIDTH NODES_SHIFT #else +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#error "Vmemmap: No space for nodes field in page flags" +#endif #define NODES_WIDTH 0 #endif @@ -454,8 +474,8 @@ static inline void set_compound_order(struct page *page, unsigned long order) #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) -#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED -#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED +#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS +#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #endif #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) @@ -504,10 +524,12 @@ static inline struct zone *page_zone(struct page *page) return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) static inline unsigned long page_to_section(struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } +#endif static inline void set_page_zone(struct page *page, enum zone_type zone) { @@ -602,9 +624,12 @@ static inline struct address_space *page_mapping(struct page *page) struct address_space *mapping = page->mapping; VM_BUG_ON(PageSlab(page)); +#ifdef CONFIG_SWAP if (unlikely(PageSwapCache(page))) mapping = &swapper_space; - else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) + else +#endif + if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) mapping = NULL; return mapping; } @@ -649,12 +674,6 @@ static inline int page_mapped(struct page *page) } /* - * Error return values for the *_nopage functions - */ -#define NOPAGE_SIGBUS (NULL) -#define NOPAGE_OOM ((struct page *) (-1)) - -/* * Error return values for the *_nopfn functions */ #define NOPFN_SIGBUS ((unsigned long) -1) @@ -720,7 +739,9 @@ struct zap_details { unsigned long truncate_count; /* Compare vm_truncate_count */ }; -struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t); +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); + unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); unsigned long unmap_vmas(struct mmu_gather **tlb, @@ -1149,6 +1170,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn); struct page *follow_page(struct vm_area_struct *, unsigned long address, unsigned int foll_flags); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index af190ceab971..29adaa781cb6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -172,6 +172,7 @@ struct mm_struct { 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) */ int map_count; /* number of VMAs */ + int core_waiters; struct rw_semaphore mmap_sem; spinlock_t page_table_lock; /* Protects page tables and some counters */ @@ -216,11 +217,10 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ /* coredumping support */ - int core_waiters; struct completion *core_startup_done, core_done; /* aio bits */ - rwlock_t ioctx_list_lock; + rwlock_t ioctx_list_lock; /* aio lock */ struct kioctx *ioctx_list; #ifdef CONFIG_CGROUP_MEM_RES_CTLR struct mem_cgroup *mem_cgroup; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f274a687c7e..aad98003176f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -3,6 +3,7 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ +#ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> @@ -15,6 +16,7 @@ #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> +#include <linux/bounds.h> #include <asm/atomic.h> #include <asm/page.h> @@ -129,6 +131,8 @@ struct per_cpu_pageset { #define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)]) #endif +#endif /* !__GENERATING_BOUNDS.H */ + enum zone_type { #ifdef CONFIG_ZONE_DMA /* @@ -177,9 +181,11 @@ enum zone_type { ZONE_HIGHMEM, #endif ZONE_MOVABLE, - MAX_NR_ZONES + __MAX_NR_ZONES }; +#ifndef __GENERATING_BOUNDS_H + /* * When a memory allocation must conform to specific limitations (such * as being suitable for DMA) the caller will pass in hints to the @@ -188,28 +194,15 @@ enum zone_type { * match the requested limits. See gfp_zone() in include/linux/gfp.h */ -/* - * Count the active zones. Note that the use of defined(X) outside - * #if and family is not necessarily defined so ensure we cannot use - * it later. Use __ZONE_COUNT to work out how many shift bits we need. - */ -#define __ZONE_COUNT ( \ - defined(CONFIG_ZONE_DMA) \ - + defined(CONFIG_ZONE_DMA32) \ - + 1 \ - + defined(CONFIG_HIGHMEM) \ - + 1 \ -) -#if __ZONE_COUNT < 2 +#if MAX_NR_ZONES < 2 #define ZONES_SHIFT 0 -#elif __ZONE_COUNT <= 2 +#elif MAX_NR_ZONES <= 2 #define ZONES_SHIFT 1 -#elif __ZONE_COUNT <= 4 +#elif MAX_NR_ZONES <= 4 #define ZONES_SHIFT 2 #else #error ZONES_SHIFT -- too many zones configured adjust calculation #endif -#undef __ZONE_COUNT struct zone { /* Fields commonly accessed by the page allocator */ @@ -393,10 +386,10 @@ static inline int zone_is_oom_locked(const struct zone *zone) * The NUMA zonelists are doubled becausse we need zonelists that restrict the * allocations to a single node for GFP_THISNODE. * - * [0 .. MAX_NR_ZONES -1] : Zonelists with fallback - * [MAZ_NR_ZONES ... MAZ_ZONELISTS -1] : No fallback (GFP_THISNODE) + * [0] : Zonelist with fallback + * [1] : No fallback (GFP_THISNODE) */ -#define MAX_ZONELISTS (2 * MAX_NR_ZONES) +#define MAX_ZONELISTS 2 /* @@ -464,11 +457,20 @@ struct zonelist_cache { unsigned long last_full_zap; /* when last zap'd (jiffies) */ }; #else -#define MAX_ZONELISTS MAX_NR_ZONES +#define MAX_ZONELISTS 1 struct zonelist_cache; #endif /* + * This struct contains information about a zone in a zonelist. It is stored + * here to avoid dereferences into large structures and lookups of tables + */ +struct zoneref { + struct zone *zone; /* Pointer to actual zone */ + int zone_idx; /* zone_idx(zoneref->zone) */ +}; + +/* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing @@ -476,34 +478,23 @@ struct zonelist_cache; * * If zlcache_ptr is not NULL, then it is just the address of zlcache, * as explained above. If zlcache_ptr is NULL, there is no zlcache. + * * + * To speed the reading of the zonelist, the zonerefs contain the zone index + * of the entry being read. Helper functions to access information given + * a struct zoneref are + * + * zonelist_zone() - Return the struct zone * for an entry in _zonerefs + * zonelist_zone_idx() - Return the index of the zone for an entry + * zonelist_node_idx() - Return the index of the node for an entry */ - struct zonelist { struct zonelist_cache *zlcache_ptr; // NULL or &zlcache - struct zone *zones[MAX_ZONES_PER_ZONELIST + 1]; // NULL delimited + struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; #ifdef CONFIG_NUMA struct zonelist_cache zlcache; // optional ... #endif }; -#ifdef CONFIG_NUMA -/* - * Only custom zonelists like MPOL_BIND need to be filtered as part of - * policies. As described in the comment for struct zonelist_cache, these - * zonelists will not have a zlcache so zlcache_ptr will not be set. Use - * that to determine if the zonelists needs to be filtered or not. - */ -static inline int alloc_should_filter_zonelist(struct zonelist *zonelist) -{ - return !zonelist->zlcache_ptr; -} -#else -static inline int alloc_should_filter_zonelist(struct zonelist *zonelist) -{ - return 0; -} -#endif /* CONFIG_NUMA */ - #ifdef CONFIG_ARCH_POPULATES_NODE_MAP struct node_active_region { unsigned long start_pfn; @@ -637,9 +628,10 @@ static inline int is_normal_idx(enum zone_type idx) static inline int is_highmem(struct zone *zone) { #ifdef CONFIG_HIGHMEM - int zone_idx = zone - zone->zone_pgdat->node_zones; - return zone_idx == ZONE_HIGHMEM || - (zone_idx == ZONE_MOVABLE && zone_movable_is_highmem()); + int zone_off = (char *)zone - (char *)zone->zone_pgdat->node_zones; + return zone_off == ZONE_HIGHMEM * sizeof(*zone) || + (zone_off == ZONE_MOVABLE * sizeof(*zone) && + zone_movable_is_highmem()); #else return 0; #endif @@ -730,32 +722,103 @@ extern struct zone *next_zone(struct zone *zone); zone; \ zone = next_zone(zone)) -#ifdef CONFIG_SPARSEMEM -#include <asm/sparsemem.h> -#endif +static inline struct zone *zonelist_zone(struct zoneref *zoneref) +{ + return zoneref->zone; +} -#if BITS_PER_LONG == 32 -/* - * with 32 bit page->flags field, we reserve 9 bits for node/zone info. - * there are 4 zones (3 bits) and this leaves 9-3=6 bits for nodes. +static inline int zonelist_zone_idx(struct zoneref *zoneref) +{ + return zoneref->zone_idx; +} + +static inline int zonelist_node_idx(struct zoneref *zoneref) +{ +#ifdef CONFIG_NUMA + /* zone_to_nid not available in this context */ + return zoneref->zone->node; +#else + return 0; +#endif /* CONFIG_NUMA */ +} + +/** + * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point + * @z - The cursor used as a starting point for the search + * @highest_zoneidx - The zone index of the highest zone to return + * @nodes - An optional nodemask to filter the zonelist with + * @zone - The first suitable zone found is returned via this parameter + * + * This function returns the next zone at or below a given zone index that is + * within the allowed nodemask using a cursor as the starting point for the + * search. The zoneref returned is a cursor that is used as the next starting + * point for future calls to next_zones_zonelist(). */ -#define FLAGS_RESERVED 9 +struct zoneref *next_zones_zonelist(struct zoneref *z, + enum zone_type highest_zoneidx, + nodemask_t *nodes, + struct zone **zone); -#elif BITS_PER_LONG == 64 -/* - * with 64 bit flags field, there's plenty of room. +/** + * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist + * @zonelist - The zonelist to search for a suitable zone + * @highest_zoneidx - The zone index of the highest zone to return + * @nodes - An optional nodemask to filter the zonelist with + * @zone - The first suitable zone found is returned via this parameter + * + * This function returns the first zone at or below a given zone index that is + * within the allowed nodemask. The zoneref returned is a cursor that can be + * used to iterate the zonelist with next_zones_zonelist. The cursor should + * not be used by the caller as it does not match the value of the zone + * returned. */ -#define FLAGS_RESERVED 32 +static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, + enum zone_type highest_zoneidx, + nodemask_t *nodes, + struct zone **zone) +{ + return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes, + zone); +} -#else +/** + * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask + * @zone - The current zone in the iterator + * @z - The current pointer within zonelist->zones being iterated + * @zlist - The zonelist being iterated + * @highidx - The zone index of the highest zone to return + * @nodemask - Nodemask allowed by the allocator + * + * This iterator iterates though all zones at or below a given zone index and + * within a given nodemask + */ +#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ + for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \ + zone; \ + z = next_zones_zonelist(z, highidx, nodemask, &zone)) \ -#error BITS_PER_LONG not defined +/** + * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index + * @zone - The current zone in the iterator + * @z - The current pointer within zonelist->zones being iterated + * @zlist - The zonelist being iterated + * @highidx - The zone index of the highest zone to return + * + * This iterator iterates though all zones at or below a given zone index. + */ +#define for_each_zone_zonelist(zone, z, zlist, highidx) \ + for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) +#ifdef CONFIG_SPARSEMEM +#include <asm/sparsemem.h> #endif #if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ !defined(CONFIG_ARCH_POPULATES_NODE_MAP) -#define early_pfn_to_nid(nid) (0UL) +static inline unsigned long early_pfn_to_nid(unsigned long pfn) +{ + return 0; +} #endif #ifdef CONFIG_FLATMEM @@ -833,6 +896,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } extern int __section_nr(struct mem_section* ms); +extern unsigned long usemap_size(void); /* * We use the lower bits of the mem_map pointer to store @@ -938,6 +1002,7 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); #define pfn_valid_within(pfn) (1) #endif +#endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _LINUX_MMZONE_H */ diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index f950921523f5..b03b27457413 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -58,7 +58,11 @@ #define MSDOS_DOTDOT ".. " /* "..", padded to MSDOS_NAME chars */ /* media of boot sector */ -#define FAT_VALID_MEDIA(x) ((0xF8 <= (x) && (x) <= 0xFF) || (x) == 0xF0) +static inline int fat_valid_media(u8 media) +{ + return 0xf8 <= media || media == 0xf0; +} + #define FAT_FIRST_ENT(s, x) ((MSDOS_SB(s)->fat_bits == 32 ? 0x0FFFFF00 : \ MSDOS_SB(s)->fat_bits == 16 ? 0xFF00 : 0xF00) | (x)) @@ -195,6 +199,7 @@ struct fat_mount_options { char *iocharset; /* Charset used for filename input/display */ unsigned short shortname; /* flags for shortname display/create rule */ unsigned char name_check; /* r = relaxed, n = normal, s = strict */ + unsigned short allow_utime;/* permission for setting the [am]time */ unsigned quiet:1, /* set = fake successful chmods and chowns */ showexec:1, /* set = only set x bit for com/exe/bat */ sys_immutable:1, /* set = system files are immutable */ @@ -232,6 +237,7 @@ struct msdos_sb_info { struct mutex fat_lock; unsigned int prev_free; /* previously allocated cluster number */ unsigned int free_clusters; /* -1 if undefined */ + unsigned int free_clus_valid; /* is free_clusters valid? */ struct fat_mount_options options; struct nls_table *nls_disk; /* Codepage used on disk */ struct nls_table *nls_io; /* Charset used for input and display */ @@ -401,7 +407,7 @@ extern int fat_generic_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg); extern const struct file_operations fat_file_operations; extern const struct inode_operations fat_file_inode_operations; -extern int fat_notify_change(struct dentry * dentry, struct iattr * attr); +extern int fat_setattr(struct dentry * dentry, struct iattr * attr); extern void fat_truncate(struct inode *inode); extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 88766e43e121..9f2d76347f19 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -204,6 +204,7 @@ void ncp_update_inode2(struct inode *, struct ncp_entry_info *); /* linux/fs/ncpfs/dir.c */ extern const struct inode_operations ncp_dir_inode_operations; extern const struct file_operations ncp_dir_operations; +extern struct dentry_operations ncp_root_dentry_operations; int ncp_conn_logged_in(struct super_block *); int ncp_date_dos2unix(__le16 time, __le16 date); void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); @@ -223,6 +224,12 @@ int ncp_disconnect(struct ncp_server *server); void ncp_lock_server(struct ncp_server *server); void ncp_unlock_server(struct ncp_server *server); +/* linux/fs/ncpfs/symlink.c */ +#if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) +extern const struct address_space_operations ncp_symlink_aops; +int ncp_symlink(struct inode*, struct dentry*, const char*); +#endif + /* linux/fs/ncpfs/file.c */ extern const struct inode_operations ncp_file_inode_operations; extern const struct file_operations ncp_file_operations; diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 905e18f4b412..848025cd7087 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -14,6 +14,8 @@ * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c. * For details of nodes_remap(), see bitmap_remap in lib/bitmap.c. + * For details of nodes_onto(), see bitmap_onto in lib/bitmap.c. + * For details of nodes_fold(), see bitmap_fold in lib/bitmap.c. * * The available nodemask operations are: * @@ -55,7 +57,9 @@ * 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) - * int nodes_remap(dst, src, old, new) *dst = map(old, new)(dst) + * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) + * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap + * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * @@ -326,6 +330,22 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } +#define nodes_onto(dst, orig, relmap) \ + __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) +static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, + const nodemask_t *relmapp, int nbits) +{ + bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); +} + +#define nodes_fold(dst, orig, sz) \ + __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) +static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, + int sz, int nbits) +{ + bitmap_fold(dstp->bits, origp->bits, sz, nbits); +} + #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f4df40038f0c..20dfed590183 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -247,6 +247,7 @@ extern struct blocking_notifier_head reboot_notifier_list; #define VT_DEALLOCATE 0x0002 /* Console will be deallocated */ #define VT_WRITE 0x0003 /* A char got output */ #define VT_UPDATE 0x0004 /* A bigger update occurred */ +#define VT_PREWRITE 0x0005 /* A char is about to be written to the console */ #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ diff --git a/include/linux/oom.h b/include/linux/oom.h index 3852436b652a..a7979baf1e39 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -23,8 +23,8 @@ enum oom_constraint { CONSTRAINT_MEMORY_POLICY, }; -extern int try_set_zone_oom(struct zonelist *zonelist); -extern void clear_zonelist_oom(struct zonelist *zonelist); +extern int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_flags); +extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order); extern int register_oom_notifier(struct notifier_block *nb); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5b30f1c1e59..590cff32415d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -6,7 +6,10 @@ #define PAGE_FLAGS_H #include <linux/types.h> +#ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> +#include <linux/bounds.h> +#endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: @@ -59,77 +62,138 @@ * extends from the high bits downwards. * * | FIELD | ... | FLAGS | - * N-1 ^ 0 - * (N-FLAGS_RESERVED) + * N-1 ^ 0 + * (NR_PAGEFLAGS) * - * The fields area is reserved for fields mapping zone, node and SPARSEMEM - * section. The boundry between these two areas is defined by - * FLAGS_RESERVED which defines the width of the fields section - * (see linux/mmzone.h). New flags must _not_ overlap with this area. + * The fields area is reserved for fields mapping zone, node (for NUMA) and + * SPARSEMEM section (for variants of SPARSEMEM that require section ids like + * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ -#define PG_locked 0 /* Page is locked. Don't touch. */ -#define PG_error 1 -#define PG_referenced 2 -#define PG_uptodate 3 +enum pageflags { + PG_locked, /* Page is locked. Don't touch. */ + PG_error, + PG_referenced, + PG_uptodate, + PG_dirty, + PG_lru, + PG_active, + PG_slab, + PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ + PG_arch_1, + PG_reserved, + PG_private, /* If pagecache, has fs-private data */ + PG_writeback, /* Page is under writeback */ +#ifdef CONFIG_PAGEFLAGS_EXTENDED + PG_head, /* A head page */ + PG_tail, /* A tail page */ +#else + PG_compound, /* A compound page */ +#endif + PG_swapcache, /* Swap page: swp_entry_t in private */ + PG_mappedtodisk, /* Has blocks allocated on-disk */ + PG_reclaim, /* To be reclaimed asap */ + PG_buddy, /* Page is free, on buddy lists */ +#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR + PG_uncached, /* Page has been mapped as uncached */ +#endif + __NR_PAGEFLAGS +}; + +#ifndef __GENERATING_BOUNDS_H + +/* + * Macros to create function definitions for page flags + */ +#define TESTPAGEFLAG(uname, lname) \ +static inline int Page##uname(struct page *page) \ + { return test_bit(PG_##lname, &page->flags); } -#define PG_dirty 4 -#define PG_lru 5 -#define PG_active 6 -#define PG_slab 7 /* slab debug (Suparna wants this) */ +#define SETPAGEFLAG(uname, lname) \ +static inline void SetPage##uname(struct page *page) \ + { set_bit(PG_##lname, &page->flags); } -#define PG_owner_priv_1 8 /* Owner use. If pagecache, fs may use*/ -#define PG_arch_1 9 -#define PG_reserved 10 -#define PG_private 11 /* If pagecache, has fs-private data */ +#define CLEARPAGEFLAG(uname, lname) \ +static inline void ClearPage##uname(struct page *page) \ + { clear_bit(PG_##lname, &page->flags); } -#define PG_writeback 12 /* Page is under writeback */ -#define PG_compound 14 /* Part of a compound page */ -#define PG_swapcache 15 /* Swap page: swp_entry_t in private */ +#define __SETPAGEFLAG(uname, lname) \ +static inline void __SetPage##uname(struct page *page) \ + { __set_bit(PG_##lname, &page->flags); } -#define PG_mappedtodisk 16 /* Has blocks allocated on-disk */ -#define PG_reclaim 17 /* To be reclaimed asap */ -#define PG_buddy 19 /* Page is free, on buddy lists */ +#define __CLEARPAGEFLAG(uname, lname) \ +static inline void __ClearPage##uname(struct page *page) \ + { __clear_bit(PG_##lname, &page->flags); } + +#define TESTSETFLAG(uname, lname) \ +static inline int TestSetPage##uname(struct page *page) \ + { return test_and_set_bit(PG_##lname, &page->flags); } + +#define TESTCLEARFLAG(uname, lname) \ +static inline int TestClearPage##uname(struct page *page) \ + { return test_and_clear_bit(PG_##lname, &page->flags); } -/* PG_readahead is only used for file reads; PG_reclaim is only for writes */ -#define PG_readahead PG_reclaim /* Reminder to do async read-ahead */ -/* PG_owner_priv_1 users should have descriptive aliases */ -#define PG_checked PG_owner_priv_1 /* Used by some filesystems */ -#define PG_pinned PG_owner_priv_1 /* Xen pinned pagetable */ +#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ + SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname) + +#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ + __SETPAGEFLAG(uname, lname) __CLEARPAGEFLAG(uname, lname) + +#define PAGEFLAG_FALSE(uname) \ +static inline int Page##uname(struct page *page) \ + { return 0; } + +#define TESTSCFLAG(uname, lname) \ + TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname) + +struct page; /* forward declaration */ + +PAGEFLAG(Locked, locked) TESTSCFLAG(Locked, locked) +PAGEFLAG(Error, error) +PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) +PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) +PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) +PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) +__PAGEFLAG(Slab, slab) +PAGEFLAG(Checked, owner_priv_1) /* Used by some filesystems */ +PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */ +PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) +PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) + __SETPAGEFLAG(Private, private) -#if (BITS_PER_LONG > 32) /* - * 64-bit-only flags build down from bit 31 - * - * 32 bit -------------------------------| FIELDS | FLAGS | - * 64 bit | FIELDS | ?????? FLAGS | - * 63 32 0 + * Only test-and-set exist for PG_writeback. The unconditional operators are + * risky: they bypass page accounting. */ -#define PG_uncached 31 /* Page has been mapped as uncached */ -#endif +TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) +__PAGEFLAG(Buddy, buddy) +PAGEFLAG(MappedToDisk, mappedtodisk) +/* PG_readahead is only used for file reads; PG_reclaim is only for writes */ +PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) +PAGEFLAG(Readahead, reclaim) /* Reminder to do async read-ahead */ + +#ifdef CONFIG_HIGHMEM /* - * Manipulation of page state flags + * Must use a macro here due to header dependency issues. page_zone() is not + * available at this point. */ -#define PageLocked(page) \ - test_bit(PG_locked, &(page)->flags) -#define SetPageLocked(page) \ - set_bit(PG_locked, &(page)->flags) -#define TestSetPageLocked(page) \ - test_and_set_bit(PG_locked, &(page)->flags) -#define ClearPageLocked(page) \ - clear_bit(PG_locked, &(page)->flags) -#define TestClearPageLocked(page) \ - test_and_clear_bit(PG_locked, &(page)->flags) - -#define PageError(page) test_bit(PG_error, &(page)->flags) -#define SetPageError(page) set_bit(PG_error, &(page)->flags) -#define ClearPageError(page) clear_bit(PG_error, &(page)->flags) - -#define PageReferenced(page) test_bit(PG_referenced, &(page)->flags) -#define SetPageReferenced(page) set_bit(PG_referenced, &(page)->flags) -#define ClearPageReferenced(page) clear_bit(PG_referenced, &(page)->flags) -#define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags) +#define PageHighMem(__p) is_highmem(page_zone(__p)) +#else +PAGEFLAG_FALSE(HighMem) +#endif + +#ifdef CONFIG_SWAP +PAGEFLAG(SwapCache, swapcache) +#else +PAGEFLAG_FALSE(SwapCache) +#endif + +#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR +PAGEFLAG(Uncached, uncached) +#else +PAGEFLAG_FALSE(Uncached) +#endif static inline int PageUptodate(struct page *page) { @@ -177,97 +241,59 @@ static inline void SetPageUptodate(struct page *page) #endif } -#define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags) - -#define PageDirty(page) test_bit(PG_dirty, &(page)->flags) -#define SetPageDirty(page) set_bit(PG_dirty, &(page)->flags) -#define TestSetPageDirty(page) test_and_set_bit(PG_dirty, &(page)->flags) -#define ClearPageDirty(page) clear_bit(PG_dirty, &(page)->flags) -#define __ClearPageDirty(page) __clear_bit(PG_dirty, &(page)->flags) -#define TestClearPageDirty(page) test_and_clear_bit(PG_dirty, &(page)->flags) - -#define PageLRU(page) test_bit(PG_lru, &(page)->flags) -#define SetPageLRU(page) set_bit(PG_lru, &(page)->flags) -#define ClearPageLRU(page) clear_bit(PG_lru, &(page)->flags) -#define __ClearPageLRU(page) __clear_bit(PG_lru, &(page)->flags) - -#define PageActive(page) test_bit(PG_active, &(page)->flags) -#define SetPageActive(page) set_bit(PG_active, &(page)->flags) -#define ClearPageActive(page) clear_bit(PG_active, &(page)->flags) -#define __ClearPageActive(page) __clear_bit(PG_active, &(page)->flags) - -#define PageSlab(page) test_bit(PG_slab, &(page)->flags) -#define __SetPageSlab(page) __set_bit(PG_slab, &(page)->flags) -#define __ClearPageSlab(page) __clear_bit(PG_slab, &(page)->flags) - -#ifdef CONFIG_HIGHMEM -#define PageHighMem(page) is_highmem(page_zone(page)) -#else -#define PageHighMem(page) 0 /* needed to optimize away at compile time */ -#endif +CLEARPAGEFLAG(Uptodate, uptodate) -#define PageChecked(page) test_bit(PG_checked, &(page)->flags) -#define SetPageChecked(page) set_bit(PG_checked, &(page)->flags) -#define ClearPageChecked(page) clear_bit(PG_checked, &(page)->flags) - -#define PagePinned(page) test_bit(PG_pinned, &(page)->flags) -#define SetPagePinned(page) set_bit(PG_pinned, &(page)->flags) -#define ClearPagePinned(page) clear_bit(PG_pinned, &(page)->flags) +extern void cancel_dirty_page(struct page *page, unsigned int account_size); -#define PageReserved(page) test_bit(PG_reserved, &(page)->flags) -#define SetPageReserved(page) set_bit(PG_reserved, &(page)->flags) -#define ClearPageReserved(page) clear_bit(PG_reserved, &(page)->flags) -#define __ClearPageReserved(page) __clear_bit(PG_reserved, &(page)->flags) +int test_clear_page_writeback(struct page *page); +int test_set_page_writeback(struct page *page); -#define SetPagePrivate(page) set_bit(PG_private, &(page)->flags) -#define ClearPagePrivate(page) clear_bit(PG_private, &(page)->flags) -#define PagePrivate(page) test_bit(PG_private, &(page)->flags) -#define __SetPagePrivate(page) __set_bit(PG_private, &(page)->flags) -#define __ClearPagePrivate(page) __clear_bit(PG_private, &(page)->flags) +static inline void set_page_writeback(struct page *page) +{ + test_set_page_writeback(page); +} +#ifdef CONFIG_PAGEFLAGS_EXTENDED /* - * Only test-and-set exist for PG_writeback. The unconditional operators are - * risky: they bypass page accounting. + * System with lots of page flags available. This allows separate + * flags for PageHead() and PageTail() checks of compound pages so that bit + * tests can be used in performance sensitive paths. PageCompound is + * generally not used in hot code paths. */ -#define PageWriteback(page) test_bit(PG_writeback, &(page)->flags) -#define TestSetPageWriteback(page) test_and_set_bit(PG_writeback, \ - &(page)->flags) -#define TestClearPageWriteback(page) test_and_clear_bit(PG_writeback, \ - &(page)->flags) +__PAGEFLAG(Head, head) +__PAGEFLAG(Tail, tail) -#define PageBuddy(page) test_bit(PG_buddy, &(page)->flags) -#define __SetPageBuddy(page) __set_bit(PG_buddy, &(page)->flags) -#define __ClearPageBuddy(page) __clear_bit(PG_buddy, &(page)->flags) - -#define PageMappedToDisk(page) test_bit(PG_mappedtodisk, &(page)->flags) -#define SetPageMappedToDisk(page) set_bit(PG_mappedtodisk, &(page)->flags) -#define ClearPageMappedToDisk(page) clear_bit(PG_mappedtodisk, &(page)->flags) - -#define PageReadahead(page) test_bit(PG_readahead, &(page)->flags) -#define SetPageReadahead(page) set_bit(PG_readahead, &(page)->flags) -#define ClearPageReadahead(page) clear_bit(PG_readahead, &(page)->flags) - -#define PageReclaim(page) test_bit(PG_reclaim, &(page)->flags) -#define SetPageReclaim(page) set_bit(PG_reclaim, &(page)->flags) -#define ClearPageReclaim(page) clear_bit(PG_reclaim, &(page)->flags) -#define TestClearPageReclaim(page) test_and_clear_bit(PG_reclaim, &(page)->flags) +static inline int PageCompound(struct page *page) +{ + return page->flags & ((1L << PG_head) | (1L << PG_tail)); -#define PageCompound(page) test_bit(PG_compound, &(page)->flags) -#define __SetPageCompound(page) __set_bit(PG_compound, &(page)->flags) -#define __ClearPageCompound(page) __clear_bit(PG_compound, &(page)->flags) +} +#else +/* + * Reduce page flag use as much as possible by overlapping + * compound page flags with the flags used for page cache pages. Possible + * because PageCompound is always set for compound pages and not for + * pages on the LRU and/or pagecache. + */ +TESTPAGEFLAG(Compound, compound) +__PAGEFLAG(Head, compound) /* * PG_reclaim is used in combination with PG_compound to mark the - * head and tail of a compound page + * head and tail of a compound page. This saves one page flag + * but makes it impossible to use compound pages for the page cache. + * The PG_reclaim bit would have to be used for reclaim or readahead + * if compound pages enter the page cache. * * PG_compound & PG_reclaim => Tail page * PG_compound & ~PG_reclaim => Head page */ - #define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim)) -#define PageTail(page) (((page)->flags & PG_head_tail_mask) \ - == PG_head_tail_mask) +static inline int PageTail(struct page *page) +{ + return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask); +} static inline void __SetPageTail(struct page *page) { @@ -279,33 +305,6 @@ static inline void __ClearPageTail(struct page *page) page->flags &= ~PG_head_tail_mask; } -#define PageHead(page) (((page)->flags & PG_head_tail_mask) \ - == (1L << PG_compound)) -#define __SetPageHead(page) __SetPageCompound(page) -#define __ClearPageHead(page) __ClearPageCompound(page) - -#ifdef CONFIG_SWAP -#define PageSwapCache(page) test_bit(PG_swapcache, &(page)->flags) -#define SetPageSwapCache(page) set_bit(PG_swapcache, &(page)->flags) -#define ClearPageSwapCache(page) clear_bit(PG_swapcache, &(page)->flags) -#else -#define PageSwapCache(page) 0 -#endif - -#define PageUncached(page) test_bit(PG_uncached, &(page)->flags) -#define SetPageUncached(page) set_bit(PG_uncached, &(page)->flags) -#define ClearPageUncached(page) clear_bit(PG_uncached, &(page)->flags) - -struct page; /* forward declaration */ - -extern void cancel_dirty_page(struct page *page, unsigned int account_size); - -int test_clear_page_writeback(struct page *page); -int test_set_page_writeback(struct page *page); - -static inline void set_page_writeback(struct page *page) -{ - test_set_page_writeback(page); -} - +#endif /* !PAGEFLAGS_EXTENDED */ +#endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ diff --git a/include/linux/prctl.h b/include/linux/prctl.h index 5c80b1939636..5ad79198d6f9 100644 --- a/include/linux/prctl.h +++ b/include/linux/prctl.h @@ -16,7 +16,8 @@ # define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */ # define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */ -/* Get/set whether or not to drop capabilities on setuid() away from uid 0 */ +/* Get/set whether or not to drop capabilities on setuid() away from + * uid 0 (as per security/commoncap.c) */ #define PR_GET_KEEPCAPS 7 #define PR_SET_KEEPCAPS 8 @@ -63,7 +64,7 @@ #define PR_GET_SECCOMP 21 #define PR_SET_SECCOMP 22 -/* Get/set the capability bounding set */ +/* Get/set the capability bounding set (as per security/commoncap.c) */ #define PR_CAPBSET_READ 23 #define PR_CAPBSET_DROP 24 @@ -73,4 +74,8 @@ # define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */ # define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */ +/* Get/set securebits (as per security/commoncap.c) */ +#define PR_GET_SECUREBITS 27 +#define PR_SET_SECUREBITS 28 + #endif /* _LINUX_PRCTL_H */ diff --git a/include/linux/quota.h b/include/linux/quota.h index eb560d031acd..52e49dce6584 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -202,10 +202,14 @@ struct quota_format_type; struct mem_dqinfo { struct quota_format_type *dqi_format; + int dqi_fmt_id; /* Id of the dqi_format - used when turning + * quotas on after remount RW */ struct list_head dqi_dirty_list; /* List of dirty dquots */ unsigned long dqi_flags; unsigned int dqi_bgrace; unsigned int dqi_igrace; + qsize_t dqi_maxblimit; + qsize_t dqi_maxilimit; union { struct v1_mem_dqinfo v1_i; struct v2_mem_dqinfo v2_i; @@ -296,8 +300,8 @@ struct dquot_operations { /* Operations handling requests from userspace */ struct quotactl_ops { - int (*quota_on)(struct super_block *, int, int, char *); - int (*quota_off)(struct super_block *, int); + int (*quota_on)(struct super_block *, int, int, char *, int); + int (*quota_off)(struct super_block *, int, int); int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); @@ -318,6 +322,10 @@ struct quota_format_type { #define DQUOT_USR_ENABLED 0x01 /* User diskquotas enabled */ #define DQUOT_GRP_ENABLED 0x02 /* Group diskquotas enabled */ +#define DQUOT_USR_SUSPENDED 0x04 /* User diskquotas are off, but + * we have necessary info in + * memory to turn them on */ +#define DQUOT_GRP_SUSPENDED 0x08 /* The same for group quotas */ struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ @@ -329,17 +337,16 @@ struct quota_info { struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; -/* Inline would be better but we need to dereference super_block which is not defined yet */ -int mark_dquot_dirty(struct dquot *dquot); - -#define dquot_dirty(dquot) test_bit(DQ_MOD_B, &(dquot)->dq_flags) - #define sb_has_quota_enabled(sb, type) ((type)==USRQUOTA ? \ (sb_dqopt(sb)->flags & DQUOT_USR_ENABLED) : (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED)) #define sb_any_quota_enabled(sb) (sb_has_quota_enabled(sb, USRQUOTA) | \ sb_has_quota_enabled(sb, GRPQUOTA)) +#define sb_has_quota_suspended(sb, type) \ + ((type) == USRQUOTA ? (sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED) : \ + (sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED)) + int register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 5110201a4159..f86702053853 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -37,11 +37,11 @@ extern int dquot_release(struct dquot *dquot); extern int dquot_commit_info(struct super_block *sb, int type); extern int dquot_mark_dquot_dirty(struct dquot *dquot); -extern int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path); +extern int vfs_quota_on(struct super_block *sb, int type, int format_id, + char *path, int remount); extern int vfs_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); -extern int vfs_quota_off(struct super_block *sb, int type); -#define vfs_quota_off_mount(sb, type) vfs_quota_off(sb, type) +extern int vfs_quota_off(struct super_block *sb, int type, int remount); extern int vfs_quota_sync(struct super_block *sb, int type); extern int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); extern int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); @@ -59,7 +59,7 @@ extern struct quotactl_ops vfs_quotactl_ops; /* It is better to call this function outside of any transaction as it might * need a lot of space in journal for dquot structure allocation. */ -static __inline__ void DQUOT_INIT(struct inode *inode) +static inline void DQUOT_INIT(struct inode *inode) { BUG_ON(!inode->i_sb); if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) @@ -67,7 +67,7 @@ static __inline__ void DQUOT_INIT(struct inode *inode) } /* The same as with DQUOT_INIT */ -static __inline__ void DQUOT_DROP(struct inode *inode) +static inline void DQUOT_DROP(struct inode *inode) { /* Here we can get arbitrary inode from clear_inode() so we have * to be careful. OTOH we don't need locking as quota operations @@ -90,7 +90,7 @@ static __inline__ void DQUOT_DROP(struct inode *inode) /* The following allocation/freeing/transfer functions *must* be called inside * a transaction (deadlocks possible otherwise) */ -static __inline__ int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) { if (sb_any_quota_enabled(inode->i_sb)) { /* Used space is updated in alloc_space() */ @@ -102,7 +102,7 @@ static __inline__ int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t return 0; } -static __inline__ int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr) +static inline int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr) { int ret; if (!(ret = DQUOT_PREALLOC_SPACE_NODIRTY(inode, nr))) @@ -110,7 +110,7 @@ static __inline__ int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr) return ret; } -static __inline__ int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) { if (sb_any_quota_enabled(inode->i_sb)) { /* Used space is updated in alloc_space() */ @@ -122,7 +122,7 @@ static __inline__ int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) return 0; } -static __inline__ int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr) +static inline int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr) { int ret; if (!(ret = DQUOT_ALLOC_SPACE_NODIRTY(inode, nr))) @@ -130,7 +130,7 @@ static __inline__ int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr) return ret; } -static __inline__ int DQUOT_ALLOC_INODE(struct inode *inode) +static inline int DQUOT_ALLOC_INODE(struct inode *inode) { if (sb_any_quota_enabled(inode->i_sb)) { DQUOT_INIT(inode); @@ -140,7 +140,7 @@ static __inline__ int DQUOT_ALLOC_INODE(struct inode *inode) return 0; } -static __inline__ void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr) +static inline void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr) { if (sb_any_quota_enabled(inode->i_sb)) inode->i_sb->dq_op->free_space(inode, nr); @@ -148,19 +148,19 @@ static __inline__ void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr) inode_sub_bytes(inode, nr); } -static __inline__ void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr) +static inline void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr) { DQUOT_FREE_SPACE_NODIRTY(inode, nr); mark_inode_dirty(inode); } -static __inline__ void DQUOT_FREE_INODE(struct inode *inode) +static inline void DQUOT_FREE_INODE(struct inode *inode) { if (sb_any_quota_enabled(inode->i_sb)) inode->i_sb->dq_op->free_inode(inode, 1); } -static __inline__ int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr) +static inline int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr) { if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) { DQUOT_INIT(inode); @@ -171,14 +171,32 @@ static __inline__ int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr) } /* The following two functions cannot be called inside a transaction */ -#define DQUOT_SYNC(sb) sync_dquots(sb, -1) +static inline void DQUOT_SYNC(struct super_block *sb) +{ + sync_dquots(sb, -1); +} -static __inline__ int DQUOT_OFF(struct super_block *sb) +static inline int DQUOT_OFF(struct super_block *sb, int remount) { int ret = -ENOSYS; - if (sb_any_quota_enabled(sb) && sb->s_qcop && sb->s_qcop->quota_off) - ret = sb->s_qcop->quota_off(sb, -1); + if (sb->s_qcop && sb->s_qcop->quota_off) + ret = sb->s_qcop->quota_off(sb, -1, remount); + return ret; +} + +static inline int DQUOT_ON_REMOUNT(struct super_block *sb) +{ + int cnt; + int ret = 0, err; + + if (!sb->s_qcop || !sb->s_qcop->quota_on) + return -ENOSYS; + for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + err = sb->s_qcop->quota_on(sb, cnt, 0, NULL, 1); + if (err < 0 && !ret) + ret = err; + } return ret; } @@ -189,13 +207,43 @@ static __inline__ int DQUOT_OFF(struct super_block *sb) */ #define sb_dquot_ops (NULL) #define sb_quotactl_ops (NULL) -#define DQUOT_INIT(inode) do { } while(0) -#define DQUOT_DROP(inode) do { } while(0) -#define DQUOT_ALLOC_INODE(inode) (0) -#define DQUOT_FREE_INODE(inode) do { } while(0) -#define DQUOT_SYNC(sb) do { } while(0) -#define DQUOT_OFF(sb) do { } while(0) -#define DQUOT_TRANSFER(inode, iattr) (0) + +static inline void DQUOT_INIT(struct inode *inode) +{ +} + +static inline void DQUOT_DROP(struct inode *inode) +{ +} + +static inline int DQUOT_ALLOC_INODE(struct inode *inode) +{ + return 0; +} + +static inline void DQUOT_FREE_INODE(struct inode *inode) +{ +} + +static inline void DQUOT_SYNC(struct super_block *sb) +{ +} + +static inline int DQUOT_OFF(struct super_block *sb, int remount) +{ + return 0; +} + +static inline int DQUOT_ON_REMOUNT(struct super_block *sb) +{ + return 0; +} + +static inline int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr) +{ + return 0; +} + static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr) { inode_add_bytes(inode, nr); @@ -235,11 +283,38 @@ static inline void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr) #endif /* CONFIG_QUOTA */ -#define DQUOT_PREALLOC_BLOCK_NODIRTY(inode, nr) DQUOT_PREALLOC_SPACE_NODIRTY(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits) -#define DQUOT_PREALLOC_BLOCK(inode, nr) DQUOT_PREALLOC_SPACE(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits) -#define DQUOT_ALLOC_BLOCK_NODIRTY(inode, nr) DQUOT_ALLOC_SPACE_NODIRTY(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits) -#define DQUOT_ALLOC_BLOCK(inode, nr) DQUOT_ALLOC_SPACE(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits) -#define DQUOT_FREE_BLOCK_NODIRTY(inode, nr) DQUOT_FREE_SPACE_NODIRTY(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits) -#define DQUOT_FREE_BLOCK(inode, nr) DQUOT_FREE_SPACE(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits) +static inline int DQUOT_PREALLOC_BLOCK_NODIRTY(struct inode *inode, qsize_t nr) +{ + return DQUOT_PREALLOC_SPACE_NODIRTY(inode, + nr << inode->i_sb->s_blocksize_bits); +} + +static inline int DQUOT_PREALLOC_BLOCK(struct inode *inode, qsize_t nr) +{ + return DQUOT_PREALLOC_SPACE(inode, + nr << inode->i_sb->s_blocksize_bits); +} + +static inline int DQUOT_ALLOC_BLOCK_NODIRTY(struct inode *inode, qsize_t nr) +{ + return DQUOT_ALLOC_SPACE_NODIRTY(inode, + nr << inode->i_sb->s_blocksize_bits); +} + +static inline int DQUOT_ALLOC_BLOCK(struct inode *inode, qsize_t nr) +{ + return DQUOT_ALLOC_SPACE(inode, + nr << inode->i_sb->s_blocksize_bits); +} + +static inline void DQUOT_FREE_BLOCK_NODIRTY(struct inode *inode, qsize_t nr) +{ + DQUOT_FREE_SPACE_NODIRTY(inode, nr << inode->i_sb->s_blocksize_bits); +} + +static inline void DQUOT_FREE_BLOCK(struct inode *inode, qsize_t nr) +{ + DQUOT_FREE_SPACE(inode, nr << inode->i_sb->s_blocksize_bits); +} #endif /* _LINUX_QUOTAOPS_ */ diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 93678f57ccbe..f0827d31ae6f 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -252,6 +252,8 @@ struct r6_state { #define STRIPE_EXPANDING 9 #define STRIPE_EXPAND_SOURCE 10 #define STRIPE_EXPAND_READY 11 +#define STRIPE_IO_STARTED 12 /* do not count towards 'bypass_count' */ +#define STRIPE_FULL_WRITE 13 /* all blocks are set to be overwritten */ /* * Operations flags (in issue order) */ @@ -316,12 +318,17 @@ struct raid5_private_data { int previous_raid_disks; struct list_head handle_list; /* stripes needing handling */ + struct list_head hold_list; /* preread ready stripes */ struct list_head delayed_list; /* stripes that have plugged requests */ struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ struct bio *retry_read_aligned; /* currently retrying aligned bios */ struct bio *retry_read_aligned_list; /* aligned bios retry list */ atomic_t preread_active_stripes; /* stripes with scheduled io */ atomic_t active_aligned_reads; + atomic_t pending_full_writes; /* full write backlog */ + int bypass_count; /* bypassed prereads */ + int bypass_threshold; /* preread nice */ + struct list_head *last_hold; /* detect hold_list promotions */ atomic_t reshape_stripes; /* stripes with pending writes for reshape */ /* unfortunately we need two cache names as we temporarily have diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 8e7eff2cd0ab..4aacaeecb56f 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2176,6 +2176,7 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg); long reiserfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); +int reiserfs_unpack(struct inode *inode, struct file *filp); /* ioctl's command */ #define REISERFS_IOC_UNPACK _IOW(0xCD,1,long) diff --git a/include/linux/sched.h b/include/linux/sched.h index 9a4f3e63e3bf..024d72b47a0c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -68,7 +68,6 @@ struct sched_param { #include <linux/smp.h> #include <linux/sem.h> #include <linux/signal.h> -#include <linux/securebits.h> #include <linux/fs_struct.h> #include <linux/compiler.h> #include <linux/completion.h> @@ -1133,7 +1132,7 @@ struct task_struct { gid_t gid,egid,sgid,fsgid; struct group_info *group_info; kernel_cap_t cap_effective, cap_inheritable, cap_permitted, cap_bset; - unsigned keep_capabilities:1; + unsigned securebits; struct user_struct *user; #ifdef CONFIG_KEYS struct key *request_key_auth; /* assumed request_key authority */ diff --git a/include/linux/securebits.h b/include/linux/securebits.h index 5b0617840fa4..c1f19dbceb05 100644 --- a/include/linux/securebits.h +++ b/include/linux/securebits.h @@ -3,28 +3,39 @@ #define SECUREBITS_DEFAULT 0x00000000 -extern unsigned securebits; - /* When set UID 0 has no special privileges. When unset, we support inheritance of root-permissions and suid-root executable under compatibility mode. We raise the effective and inheritable bitmasks *of the executable file* if the effective uid of the new process is 0. If the real uid is 0, we raise the inheritable bitmask of the executable file. */ -#define SECURE_NOROOT 0 +#define SECURE_NOROOT 0 +#define SECURE_NOROOT_LOCKED 1 /* make bit-0 immutable */ /* When set, setuid to/from uid 0 does not trigger capability-"fixes" to be compatible with old programs relying on set*uid to loose privileges. When unset, setuid doesn't change privileges. */ -#define SECURE_NO_SETUID_FIXUP 2 +#define SECURE_NO_SETUID_FIXUP 2 +#define SECURE_NO_SETUID_FIXUP_LOCKED 3 /* make bit-2 immutable */ + +/* When set, a process can retain its capabilities even after + transitioning to a non-root user (the set-uid fixup suppressed by + bit 2). Bit-4 is cleared when a process calls exec(); setting both + bit 4 and 5 will create a barrier through exec that no exec()'d + child can use this feature again. */ +#define SECURE_KEEP_CAPS 4 +#define SECURE_KEEP_CAPS_LOCKED 5 /* make bit-4 immutable */ /* Each securesetting is implemented using two bits. One bit specify whether the setting is on or off. The other bit specify whether the setting is fixed or not. A setting which is fixed cannot be changed from user-level. */ +#define issecure_mask(X) (1 << (X)) +#define issecure(X) (issecure_mask(X) & current->securebits) -#define issecure(X) ( (1 << (X+1)) & SECUREBITS_DEFAULT ? \ - (1 << (X)) & SECUREBITS_DEFAULT : \ - (1 << (X)) & securebits ) +#define SECURE_ALL_BITS (issecure_mask(SECURE_NOROOT) | \ + issecure_mask(SECURE_NO_SETUID_FIXUP) | \ + issecure_mask(SECURE_KEEP_CAPS)) +#define SECURE_ALL_LOCKS (SECURE_ALL_BITS << 1) #endif /* !_LINUX_SECUREBITS_H */ diff --git a/include/linux/security.h b/include/linux/security.h index a90c06376eec..d0a28fd1747a 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -34,8 +34,6 @@ #include <linux/xfrm.h> #include <net/flow.h> -extern unsigned securebits; - /* Maximum number of letters for an LSM name string */ #define SECURITY_NAME_MAX 10 @@ -61,6 +59,8 @@ extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); extern int cap_task_post_setuid(uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags); extern void cap_task_reparent_to_init(struct task_struct *p); +extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5, long *rc_p); extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp); extern int cap_task_setioprio(struct task_struct *p, int ioprio); extern int cap_task_setnice(struct task_struct *p, int nice); @@ -720,7 +720,9 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @arg3 contains a argument. * @arg4 contains a argument. * @arg5 contains a argument. - * Return 0 if permission is granted. + * @rc_p contains a pointer to communicate back the forced return code + * Return 0 if permission is granted, and non-zero if the security module + * has taken responsibility (setting *rc_p) for the prctl call. * @task_reparent_to_init: * Set the security attributes in @p->security for a kernel thread that * is being reparented to the init task. @@ -1420,7 +1422,7 @@ struct security_operations { int (*task_wait) (struct task_struct *p); int (*task_prctl) (int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, - unsigned long arg5); + unsigned long arg5, long *rc_p); void (*task_reparent_to_init) (struct task_struct *p); void (*task_to_inode) (struct task_struct *p, struct inode *inode); @@ -1684,7 +1686,7 @@ int security_task_kill(struct task_struct *p, struct siginfo *info, int sig, u32 secid); int security_task_wait(struct task_struct *p); int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5); + unsigned long arg4, unsigned long arg5, long *rc_p); void security_task_reparent_to_init(struct task_struct *p); void security_task_to_inode(struct task_struct *p, struct inode *inode); int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); @@ -2271,9 +2273,9 @@ static inline int security_task_wait(struct task_struct *p) static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, - unsigned long arg5) + unsigned long arg5, long *rc_p) { - return 0; + return cap_task_prctl(option, arg2, arg3, arg3, arg5, rc_p); } static inline void security_task_reparent_to_init(struct task_struct *p) diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 00b65c0a82ca..3d37c94abbc8 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -46,6 +46,7 @@ enum { PLAT8250_DEV_HUB6, PLAT8250_DEV_MCA, PLAT8250_DEV_AU1X00, + PLAT8250_DEV_SM501, }; /* diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 8d5fb36ea047..f2d12d5a21b8 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -34,8 +34,7 @@ struct shmem_sb_info { uid_t uid; /* Mount uid for root directory */ gid_t gid; /* Mount gid for root directory */ mode_t mode; /* Mount mode for root directory */ - int policy; /* Default NUMA memory alloc policy */ - nodemask_t policy_nodes; /* nodemask for preferred and bind */ + struct mempolicy *mpol; /* default memory policy for mappings */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 1d7d4c5797ee..a6977423baf7 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -12,11 +12,22 @@ #include <asm/errno.h> #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) +extern void pm_set_vt_switch(int); extern int pm_prepare_console(void); extern void pm_restore_console(void); #else -static inline int pm_prepare_console(void) { return 0; } -static inline void pm_restore_console(void) {} +static inline void pm_set_vt_switch(int do_switch) +{ +} + +static inline int pm_prepare_console(void) +{ + return 0; +} + +static inline void pm_restore_console(void) +{ +} #endif typedef int __bitwise suspend_state_t; diff --git a/include/linux/swap.h b/include/linux/swap.h index 878459ae0454..0b3377650c85 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -177,11 +177,11 @@ extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern int lru_add_drain_all(void); -extern int rotate_reclaimable_page(struct page *page); +extern void rotate_reclaimable_page(struct page *page); extern void swap_setup(void); /* linux/mm/vmscan.c */ -extern unsigned long try_to_free_pages(struct zone **zones, int order, +extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, gfp_t gfp_mask); diff --git a/include/linux/synclink.h b/include/linux/synclink.h index 5562fbf72095..45f6bc82d317 100644 --- a/include/linux/synclink.h +++ b/include/linux/synclink.h @@ -13,10 +13,6 @@ #define _SYNCLINK_H_ #define SYNCLINK_H_VERSION 3.6 -#define BOOLEAN int -#define TRUE 1 -#define FALSE 0 - #define BIT0 0x0001 #define BIT1 0x0002 #define BIT2 0x0004 diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ce8e7da05807..364789aae9f3 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -31,6 +31,7 @@ struct vm_struct { struct page **pages; unsigned int nr_pages; unsigned long phys_addr; + void *caller; }; /* @@ -66,6 +67,8 @@ static inline size_t get_vm_area_size(const struct vm_struct *area) } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); +extern struct vm_struct *get_vm_area_caller(unsigned long size, + unsigned long flags, void *caller); extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end); extern struct vm_struct *get_vm_area_node(unsigned long size, @@ -87,4 +90,6 @@ extern void free_vm_area(struct vm_struct *area); extern rwlock_t vmlist_lock; extern struct vm_struct *vmlist; +extern const struct seq_operations vmalloc_op; + #endif /* _LINUX_VMALLOC_H */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9f1b4b46151e..e83b69346d23 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -25,6 +25,7 @@ #define HIGHMEM_ZONE(xx) #endif + #define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, @@ -37,6 +38,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGSCAN_DIRECT), PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL, PAGEOUTRUN, ALLOCSTALL, PGROTATED, +#ifdef CONFIG_HUGETLB_PAGE + HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, +#endif NR_VM_EVENT_ITEMS }; @@ -174,7 +178,7 @@ static inline unsigned long node_page_state(int node, zone_page_state(&zones[ZONE_MOVABLE], item); } -extern void zone_statistics(struct zonelist *, struct zone *); +extern void zone_statistics(struct zone *, struct zone *); #else |