diff options
| author | Scott Wood <scottwood@freescale.com> | 2015-02-13 22:30:07 (GMT) |
|---|---|---|
| committer | Scott Wood <scottwood@freescale.com> | 2015-02-13 22:30:07 (GMT) |
| commit | e5fc662387b40984ed4b7a14477cc659f4d80b94 (patch) | |
| tree | cf60ec2e653100003e59216306e241a4485c7d4f /include/linux | |
| parent | fa2b857e85998a6843c1a6843446ff00067fa3a4 (diff) | |
| parent | 38bff34aef9a92ba18386e801604824856883b32 (diff) | |
| download | linux-fsl-qoriq-e5fc662387b40984ed4b7a14477cc659f4d80b94.tar.xz | |
Merge branch 'rtmerge'
Signed-off-by: Scott Wood <scottwood@freescale.com>
Conflicts:
arch/arm/kvm/mmu.c
arch/arm/mm/proc-v7-3level.S
arch/powerpc/kernel/vdso32/getcpu.S
drivers/crypto/caam/error.c
drivers/crypto/caam/sg_sw_sec4.h
drivers/usb/host/ehci-fsl.c
Diffstat (limited to 'include/linux')
86 files changed, 1041 insertions, 298 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index 4fb28b2..c25cb64d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -46,6 +46,7 @@ struct audit_tree; struct audit_krule { int vers_ops; + u32 pflags; u32 flags; u32 listnr; u32 action; @@ -63,6 +64,9 @@ struct audit_krule { u64 prio; }; +/* Flag to indicate legacy AUDIT_LOGINUID unset usage */ +#define AUDIT_LOGINUID_LEGACY 0x1 + struct audit_field { u32 type; u32 val; diff --git a/include/linux/bio.h b/include/linux/bio.h index ec48bac..6c17ad5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -187,6 +187,7 @@ struct bio_integrity_payload { unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_idx; /* current bip_vec index */ + unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned bip_owns_buf:1; /* should free bip_buf */ struct work_struct bip_work; /* I/O completion */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0e6f765..b105678 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1198,10 +1198,9 @@ static inline int queue_alignment_offset(struct request_queue *q) static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = (sector << 9) & (granularity - 1); + unsigned int alignment = sector_div(sector, granularity >> 9) << 9; - return (granularity + lim->alignment_offset - alignment) - & (granularity - 1); + return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) diff --git a/include/linux/capability.h b/include/linux/capability.h index a6ee1f9..aa93e5e 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -78,8 +78,11 @@ extern const kernel_cap_t __cap_init_eff_set; # error Fix up hand-coded capability macro initializers #else /* HAND-CODED capability initializers */ +#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1) +#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1) + # define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }}) -# define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }}) +# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }}) # define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \ | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \ CAP_FS_MASK_B1 } }) @@ -210,7 +213,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); -extern bool inode_capable(const struct inode *inode, int cap); +extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); /* audit system wants to get cap info from files as well */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index dbbf8aa..4802826 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -289,7 +289,7 @@ extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); -extern struct clocksource * __init __weak clocksource_default_clock(void); +extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); extern void diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 091d72e..01e3132 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, - bool sync, bool *contended); + enum migrate_mode mode, bool *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -62,6 +62,22 @@ static inline bool compaction_deferred(struct zone *zone, int order) return zone->compact_considered < defer_limit; } +/* + * Update defer tracking counters after successful compaction of given order, + * which means an allocation either succeeded (alloc_success == true) or is + * expected to succeed. + */ +static inline void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success) +{ + if (alloc_success) { + zone->compact_considered = 0; + zone->compact_defer_shift = 0; + } + if (order >= zone->compact_order_failed) + zone->compact_order_failed = order + 1; +} + /* Returns true if restarting compaction after many failures */ static inline bool compaction_restarting(struct zone *zone, int order) { @@ -75,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { return COMPACT_CONTINUE; } diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 24545cd..02ae99e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -37,6 +37,9 @@ __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ (typeof(ptr)) (__ptr + (off)); }) +/* Make the optimizer believe the variable can be manipulated arbitrarily. */ +#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var)) + #ifdef __CHECKER__ #define __must_be_array(arr) 0 #else diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h new file mode 100644 index 0000000..cdd1cc2 --- /dev/null +++ b/include/linux/compiler-gcc5.h @@ -0,0 +1,66 @@ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead." +#endif + +#define __used __attribute__((__used__)) +#define __must_check __attribute__((warn_unused_result)) +#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) + +/* Mark functions as cold. gcc will assume any path leading to a call + to them will be unlikely. This means a lot of manual unlikely()s + are unnecessary now for any paths leading to the usual suspects + like BUG(), printk(), panic() etc. [but let's keep them for now for + older compilers] + + Early snapshots of gcc 4.3 don't support this and we can't detect this + in the preprocessor, but we can live with this because they're unreleased. + Maketime probing would be overkill here. + + gcc also has a __attribute__((__hot__)) to move hot functions into + a special section, but I don't see any sense in this right now in + the kernel context */ +#define __cold __attribute__((__cold__)) + +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ + +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() + +/* Mark a function definition as prohibited from being cloned. */ +#define __noclone __attribute__((__noclone__)) + +/* + * Tell the optimizer that something else uses this function or variable. + */ +#define __visible __attribute__((externally_visible)) + +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * Fixed in GCC 4.8.2 and later versions. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#define __HAVE_BUILTIN_BSWAP16__ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index dc1bd3d..5529c52 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -15,6 +15,7 @@ */ #undef barrier #undef RELOC_HIDE +#undef OPTIMIZER_HIDE_VAR #define barrier() __memory_barrier() @@ -23,6 +24,12 @@ __ptr = (unsigned long) (ptr); \ (typeof(ptr)) (__ptr + (off)); }) +/* This should act as an optimization barrier on var. + * Given that this compiler does not have inline assembly, a compiler barrier + * is the best we can do. + */ +#define OPTIMIZER_HIDE_VAR(var) barrier() + /* Intel ECC compiler doesn't support __builtin_types_compatible_p() */ #define __must_be_array(a) 0 diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 92669cd..a2329c5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -170,6 +170,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); (typeof(ptr)) (__ptr + (off)); }) #endif +#ifndef OPTIMIZER_HIDE_VAR +#define OPTIMIZER_HIDE_VAR(var) barrier() +#endif + /* Not-quite-unique ID. */ #ifndef __UNIQUE_ID # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index cc1b01c..a7ebb89 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -12,10 +12,31 @@ #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> +#include <linux/jump_label.h> #ifdef CONFIG_CPUSETS -extern int number_of_cpusets; /* How many cpusets are defined in system? */ +extern struct static_key cpusets_enabled_key; +static inline bool cpusets_enabled(void) +{ + return static_key_false(&cpusets_enabled_key); +} + +static inline int nr_cpusets(void) +{ + /* jump label reference count + the top-level cpuset */ + return static_key_count(&cpusets_enabled_key) + 1; +} + +static inline void cpuset_inc(void) +{ + static_key_slow_inc(&cpusets_enabled_key); +} + +static inline void cpuset_dec(void) +{ + static_key_slow_dec(&cpusets_enabled_key); +} extern int cpuset_init(void); extern void cpuset_init_smp(void); @@ -32,13 +53,13 @@ extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask); static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_softwall(node, gfp_mask); } static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_hardwall(node, gfp_mask); } @@ -87,25 +108,26 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); /* - * get_mems_allowed is required when making decisions involving mems_allowed - * such as during page allocation. mems_allowed can be updated in parallel - * and depending on the new value an operation can fail potentially causing - * process failure. A retry loop with get_mems_allowed and put_mems_allowed - * prevents these artificial failures. + * read_mems_allowed_begin is required when making decisions involving + * mems_allowed such as during page allocation. mems_allowed can be updated in + * parallel and depending on the new value an operation can fail potentially + * causing process failure. A retry loop with read_mems_allowed_begin and + * read_mems_allowed_retry prevents these artificial failures. */ -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return read_seqcount_begin(¤t->mems_allowed_seq); } /* - * If this returns false, the operation that took place after get_mems_allowed - * may have failed. It is up to the caller to retry the operation if + * If this returns true, the operation that took place after + * read_mems_allowed_begin may have failed artificially due to a concurrent + * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return !read_seqcount_retry(¤t->mems_allowed_seq, seq); + return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) @@ -119,6 +141,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) #else /* !CONFIG_CPUSETS */ +static inline bool cpusets_enabled(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} @@ -221,14 +245,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return 0; } -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return true; + return false; } #endif /* !CONFIG_CPUSETS */ diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 7032518..60023e5 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -14,14 +14,13 @@ extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; -extern int __weak elfcorehdr_alloc(unsigned long long *addr, - unsigned long long *size); -extern void __weak elfcorehdr_free(unsigned long long addr); -extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos); -extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); -extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, - unsigned long from, unsigned long pfn, - unsigned long size, pgprot_t prot); +extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); +extern void elfcorehdr_free(unsigned long long addr); +extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); +extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot); extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); diff --git a/include/linux/cred.h b/include/linux/cred.h index 04421e8..6c58dd7 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -68,6 +68,7 @@ extern void groups_free(struct group_info *); extern int set_current_groups(struct group_info *); extern int set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); +extern bool may_setgroups(void); /* access the groups "array" with this macro */ #define GROUP_AT(gi, i) \ diff --git a/include/linux/crypto.h b/include/linux/crypto.h index b81b096..df663e5 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -26,6 +26,19 @@ #include <linux/uaccess.h> /* + * Autoloaded crypto modules should only use a prefixed name to avoid allowing + * arbitrary modules to be loaded. Loading from userspace may still need the + * unprefixed names, so retains those aliases as well. + * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 + * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro + * expands twice on the same line. Instead, use a separate base name for the + * alias. + */ +#define MODULE_ALIAS_CRYPTO(name) \ + __MODULE_INFO(alias, alias_userspace, name); \ + __MODULE_INFO(alias, alias_crypto, "crypto-" name) + +/* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 59066e0..53c1b60 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -122,15 +122,15 @@ struct dentry { void *d_fsdata; /* fs-specific data */ struct list_head d_lru; /* LRU list */ + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ /* - * d_child and d_rcu can share memory + * d_alias and d_rcu can share memory */ union { - struct list_head d_child; /* child of parent list */ + struct hlist_node d_alias; /* inode alias list */ struct rcu_head d_rcu; } d_u; - struct list_head d_subdirs; /* our children */ - struct hlist_node d_alias; /* inode alias list */ }; /* @@ -211,6 +211,8 @@ struct dentry_operations { #define DCACHE_LRU_LIST 0x80000 #define DCACHE_DENTRY_KILLED 0x100000 +#define DCACHE_MAY_FREE 0x00800000 + extern seqlock_t rename_lock; static inline int dname_external(const struct dentry *dentry) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 3a8d0a2..ec951f9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -97,6 +97,20 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask) } #endif +/* + * Set both the DMA mask and the coherent DMA mask to the same thing. + * Note that we don't check the return value from dma_set_coherent_mask() + * as the DMA API guarantees that the coherent DMA mask can be set to + * the same or smaller than the streaming DMA mask. + */ +static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask) +{ + int rc = dma_set_mask(dev, mask); + if (rc == 0) + dma_set_coherent_mask(dev, mask); + return rc; +} + extern u64 dma_get_required_mask(struct device *dev); static inline unsigned int dma_get_max_seg_size(struct device *dev) diff --git a/include/linux/fs.h b/include/linux/fs.h index 164d2a9..9cb726a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2217,7 +2217,13 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); -extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); +static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count) +{ + if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) + return 0; + return vfs_fsync_range(file, pos, pos + count - 1, + (file->f_flags & __O_SYNC) ? 0 : 1); +} extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK @@ -2490,6 +2496,9 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, void inode_dio_wait(struct inode *inode); void inode_dio_done(struct inode *inode); +extern void inode_set_flags(struct inode *inode, unsigned int flags, + unsigned int mask); + extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9f15c00..e68db4d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -524,6 +524,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); +extern void ftrace_module_init(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); @@ -533,6 +534,7 @@ static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_release_mod(struct module *mod) {} +static inline void ftrace_module_init(struct module *mod) {} static inline int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 9b4dd49..fa7ac98 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -364,8 +364,8 @@ void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -extern void free_hot_cold_page(struct page *page, int cold); -extern void free_hot_cold_page_list(struct list_head *list, int cold); +extern void free_hot_cold_page(struct page *page, bool cold); +extern void free_hot_cold_page_list(struct list_head *list, bool cold); extern void __free_memcg_kmem_pages(struct page *page, unsigned int order); extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order); diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 32ba451..c32411b 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -21,6 +21,8 @@ #include <linux/hid.h> #include <linux/hid-sensor-ids.h> +#include <linux/iio/iio.h> +#include <linux/iio/trigger.h> /** * struct hid_sensor_hub_attribute_info - Attribute info @@ -166,6 +168,7 @@ struct hid_sensor_common { struct platform_device *pdev; unsigned usage_id; bool data_ready; + struct iio_trigger *trigger; struct hid_sensor_hub_attribute_info poll; struct hid_sensor_hub_attribute_info report_state; struct hid_sensor_hub_attribute_info power_state; diff --git a/include/linux/hid.h b/include/linux/hid.h index 31b9d29..00c88fc 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -286,6 +286,7 @@ struct hid_item { #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 #define HID_QUIRK_NO_INIT_INPUT_REPORTS 0x00000200 +#define HID_QUIRK_ALWAYS_POLL 0x00000400 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a291552..aac671b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -92,10 +92,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #endif /* CONFIG_DEBUG_VM */ extern unsigned long transparent_hugepage_flags; -extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end); extern int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6125579..511b1a0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -387,15 +387,23 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -int pmd_huge_support(void); -/* - * Currently hugepage migration is enabled only for pmd-based hugepage. - * This function will be updated when hugepage migration is more widely - * supported. - */ static inline int hugepage_migration_support(struct hstate *h) { - return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT); +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + return huge_page_shift(h) == PMD_SHIFT; +#else + return 0; +#endif +} + +static inline bool hugepages_supported(void) +{ + /* + * Some platform decide whether they support huge pages at boot + * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when + * there is no such support + */ + return HPAGE_SHIFT != 0; } #else /* CONFIG_HUGETLB_PAGE */ @@ -425,7 +433,6 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) -#define pmd_huge_support() 0 #define hugepage_migration_support(h) 0 #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index d98503b..b6043a0 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -473,15 +473,18 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, * 0 . 13 (Windows Server 2008) * 1 . 1 (Windows 7) * 2 . 4 (Windows 8) + * 3 . 0 (Windows 8 R2) */ #define VERSION_WS2008 ((0 << 16) | (13)) #define VERSION_WIN7 ((1 << 16) | (1)) #define VERSION_WIN8 ((2 << 16) | (4)) +#define VERSION_WIN8_1 ((3 << 16) | (0)) + #define VERSION_INVAL -1 -#define VERSION_CURRENT VERSION_WIN8 +#define VERSION_CURRENT VERSION_WIN8_1 /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) @@ -884,7 +887,7 @@ struct vmbus_channel_relid_released { struct vmbus_channel_initiate_contact { struct vmbus_channel_message_header header; u32 vmbus_version_requested; - u32 padding2; + u32 target_vcpu; /* The VCPU the host should respond to */ u64 interrupt_page; u64 monitor_page1; u64 monitor_page2; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index a899dc2..a6aa970 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -194,6 +194,7 @@ struct team { bool user_carrier_enabled; bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ + bool port_mtu_change_allowed; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 715c343..0bd3943 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -90,7 +90,6 @@ extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern bool vlan_do_receive(struct sk_buff **skb); -extern struct sk_buff *vlan_untag(struct sk_buff *skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); @@ -126,11 +125,6 @@ static inline bool vlan_do_receive(struct sk_buff **skb) return false; } -static inline struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - return skb; -} - static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h index 13ce220..593ae7c 100644 --- a/include/linux/iio/events.h +++ b/include/linux/iio/events.h @@ -90,7 +90,7 @@ enum iio_event_direction { #define IIO_EVENT_CODE_EXTRACT_TYPE(mask) ((mask >> 56) & 0xFF) -#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0xCF) +#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0x7F) #define IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(mask) ((mask >> 32) & 0xFF) diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 369cf2c..68f46cd 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -84,10 +84,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig) put_device(&trig->dev); } -static inline void iio_trigger_get(struct iio_trigger *trig) +static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig) { get_device(&trig->dev); __module_get(trig->ops->owner); + + return trig; } /** diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 79640e0..f738f92 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -234,7 +234,7 @@ static inline void in_dev_put(struct in_device *idev) static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) - return htonl(~((1<<(32-logmask))-1)); + return htonl(~((1U<<(32-logmask))-1)); return 0; } diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 766558a..a85cceb 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -40,6 +40,7 @@ extern struct fs_struct init_fs; #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ + .thread_head = LIST_HEAD_INIT(init_task.thread_node), \ .wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\ .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ @@ -221,6 +222,7 @@ extern struct task_group root_task_group; [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ }, \ .thread_group = LIST_HEAD_INIT(tsk.thread_group), \ + .thread_node = LIST_HEAD_INIT(init_signals.thread_head), \ INIT_IDS \ INIT_PERF_EVENTS(tsk) \ INIT_TRACE_IRQFLAGS \ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a2609fb..750d1e6 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -200,7 +200,40 @@ static inline int check_wakeup_irqs(void) { return 0; } extern cpumask_var_t irq_default_affinity; -extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask); +/* Internal implementation. Use the helpers below */ +extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask, + bool force); + +/** + * irq_set_affinity - Set the irq affinity of a given irq + * @irq: Interrupt to set affinity + * @mask: cpumask + * + * Fails if cpumask does not contain an online CPU + */ +static inline int +irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return __irq_set_affinity(irq, cpumask, false); +} + +/** + * irq_force_affinity - Force the irq affinity of a given irq + * @irq: Interrupt to set affinity + * @mask: cpumask + * + * Same as irq_set_affinity, but without checking the mask against + * online cpus. + * + * Solely for low level cpu hotplug code, where we need to make per + * cpu interrupts affine before the cpu becomes online. + */ +static inline int +irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return __irq_set_affinity(irq, cpumask, true); +} + extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); @@ -237,6 +270,11 @@ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) return -EINVAL; } +static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return 0; +} + static inline int irq_can_set_affinity(unsigned int irq) { return 0; diff --git a/include/linux/irq.h b/include/linux/irq.h index e2d8789..7a08e31 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -383,7 +383,8 @@ extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); extern void irq_cpu_online(void); extern void irq_cpu_offline(void); -extern int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask); +extern int irq_set_affinity_locked(struct irq_data *data, + const struct cpumask *cpumask, bool force); #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index da992bc..6686311 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -27,6 +27,8 @@ struct irq_desc; * @irq_count: stats field to detect stalled irqs * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts + * @threads_handled: stats field for deferred spurious detection of threaded handlers + * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers * @lock: locking for SMP * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes @@ -52,6 +54,8 @@ struct irq_desc { unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; u64 random_ip; raw_spinlock_t lock; struct cpumask *percpu_enabled; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5b50a1..0dae71e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -159,7 +159,11 @@ typedef struct journal_header_s * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * - * Checksum v1 and v2 are mutually exclusive features. + * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses + * journal_block_tag3_t to store a full 32-bit checksum. Everything else + * is the same as v2. + * + * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; @@ -179,6 +183,14 @@ struct commit_header { * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ +typedef struct journal_block_tag3_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ + __be32 t_checksum; /* crc32c(uuid+seq+block) */ +} journal_block_tag3_t; + typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ @@ -187,9 +199,6 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) -#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t)) - /* Tail of descriptor block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ @@ -284,6 +293,7 @@ typedef struct journal_superblock_s #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 +#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM @@ -291,7 +301,8 @@ typedef struct journal_superblock_s #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ - JBD2_FEATURE_INCOMPAT_CSUM_V2) + JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ + JBD2_FEATURE_INCOMPAT_CSUM_V3) #ifdef __KERNEL__ @@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y) extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); +static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) +{ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) || + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return 1; + + return 0; +} + /* * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for * transaction control blocks. diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d235e88..8acbb7b 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -258,23 +258,11 @@ extern unsigned long preset_lpj; #define SEC_JIFFIE_SC (32 - SHIFT_HZ) #endif #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) -#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19) #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) -#define USEC_CONVERSION \ - ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) -/* - * USEC_ROUND is used in the timeval to jiffie conversion. See there - * for more details. It is the scaled resolution rounding value. Note - * that it is a 64-bit value. Since, when it is applied, we are already - * in jiffies (albit scaled), it is nothing but the bits we will shift - * off. - */ -#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1) /* * The maximum jiffie value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 006627b..c5f7962 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -63,6 +63,10 @@ struct static_key { # include <asm/jump_label.h> # define HAVE_JUMP_LABEL +#else +struct static_key { + atomic_t enabled; +}; #endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ enum jump_label_type { @@ -73,6 +77,12 @@ enum jump_label_type { struct module; #include <linux/atomic.h> + +static inline int static_key_count(struct static_key *key) +{ + return atomic_read(&key->enabled); +} + #ifdef HAVE_JUMP_LABEL #define JUMP_LABEL_TRUE_BRANCH 1UL @@ -123,24 +133,20 @@ extern void jump_label_apply_nops(struct module *mod); #else /* !HAVE_JUMP_LABEL */ -struct static_key { - atomic_t enabled; -}; - static __always_inline void jump_label_init(void) { } static __always_inline bool static_key_false(struct static_key *key) { - if (unlikely(atomic_read(&key->enabled)) > 0) + if (unlikely(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { - if (likely(atomic_read(&key->enabled)) > 0) + if (likely(static_key_count(key) > 0)) return true; return false; } @@ -180,7 +186,7 @@ static inline int jump_label_apply_nops(struct module *mod) static inline bool static_key_enabled(struct static_key *key) { - return (atomic_read(&key->enabled) > 0); + return static_key_count(key) > 0; } #endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 51c72be..4b2053a 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -74,6 +74,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu) * Number of interrupts per specific IRQ source, since bootup */ extern unsigned int kstat_irqs(unsigned int irq); +extern unsigned int kstat_irqs_usr(unsigned int irq); /* * Number of interrupts per cpu, since bootup diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index c6e091b..bdfc95b 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -283,7 +283,7 @@ struct kgdb_io { extern struct kgdb_arch arch_kgdb_ops; -extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); +extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); #ifdef CONFIG_SERIAL_KGDB_NMI extern int kgdb_register_nmi_console(void); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e2af2eb..b26594b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -464,8 +464,6 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); -void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new, - u64 last_generation); static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { diff --git a/include/linux/libata.h b/include/linux/libata.h index 5e17d08..47938b0 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -596,6 +596,7 @@ struct ata_host { struct device *dev; void __iomem * const *iomap; unsigned int n_ports; + unsigned int n_tags; /* nr of NCQ tags */ void *private_data; struct ata_port_operations *ops; unsigned long flags; @@ -825,6 +826,7 @@ struct ata_port { unsigned long qc_allocated; unsigned int qc_active; int nr_active_links; /* #links with active qcs */ + unsigned int last_tag; /* track next tag hw expects */ struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ diff --git a/include/linux/list.h b/include/linux/list.h index 885943e..2c2cbc1 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -384,6 +384,22 @@ static inline void list_splice_tail_init(struct list_head *list, list_entry((ptr)->prev, type, member) /** + * list_next_entry - get the next element in list + * @pos: the type * to cursor + * @member: the name of the list_struct within the struct. + */ +#define list_next_entry(pos, member) \ + list_entry((pos)->member.next, typeof(*(pos)), member) + +/** + * list_prev_entry - get the prev element in list + * @pos: the type * to cursor + * @member: the name of the list_struct within the struct. + */ +#define list_prev_entry(pos, member) \ + list_entry((pos)->member.prev, typeof(*(pos)), member) + +/** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index da6716b..ccc1b71 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -175,6 +175,12 @@ static inline int vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return 0; + +#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + if (vma->vm_flags & VM_HUGETLB) + return 0; +#endif + /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not diff --git a/include/linux/migrate.h b/include/linux/migrate.h index ee8b14a..449905e 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -5,7 +5,9 @@ #include <linux/mempolicy.h> #include <linux/migrate_mode.h> -typedef struct page *new_page_t(struct page *, unsigned long private, int **); +typedef struct page *new_page_t(struct page *page, unsigned long private, + int **reason); +typedef void free_page_t(struct page *page, unsigned long private); /* * Return values from addresss_space_operations.migratepage(): @@ -39,7 +41,7 @@ extern void putback_lru_pages(struct list_head *l); extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); -extern int migrate_pages(struct list_head *l, new_page_t x, +extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern int fail_migrate_page(struct address_space *, @@ -61,8 +63,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline void putback_movable_pages(struct list_head *l) {} -static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, enum migrate_mode mode, int reason) +static inline int migrate_pages(struct list_head *l, new_page_t new, + free_page_t free, unsigned long private, enum migrate_mode mode, + int reason) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 2acbab4..2e577bd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -919,6 +919,14 @@ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_zero_setup(struct vm_area_struct *); +#ifdef CONFIG_SHMEM +bool shmem_mapping(struct address_space *mapping); +#else +static inline bool shmem_mapping(struct address_space *mapping) +{ + return false; +} +#endif extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); @@ -1001,6 +1009,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); @@ -1655,9 +1664,6 @@ void page_cache_async_readahead(struct address_space *mapping, unsigned long size); unsigned long max_sane_readahead(unsigned long nr); -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, - struct file *filp); /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -1668,7 +1674,7 @@ extern int expand_downwards(struct vm_area_struct *vma, #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else - #define expand_upwards(vma, address) do { } while (0) + #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d87823c..a9c83ee 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -329,9 +329,9 @@ struct mm_rss_stat { struct kioctx_table; struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ + struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bd791e4..450f19c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -75,9 +75,18 @@ enum { extern int page_group_by_mobility_disabled; -static inline int get_pageblock_migratetype(struct page *page) +#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) +#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) + +#define get_pageblock_migratetype(page) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + PB_migrate_end, MIGRATETYPE_MASK) + +static inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) { - return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); + BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); + return get_pfnblock_flags_mask(page, pfn, PB_migrate_end, + MIGRATETYPE_MASK); } struct free_area { @@ -134,6 +143,7 @@ enum zone_stat_item { NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -312,19 +322,12 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H struct zone { - /* Fields commonly accessed by the page allocator */ + /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long watermark[NR_WMARK]; /* - * When free pages are below this point, additional steps are taken - * when reading the number of free pages to avoid per-cpu counter - * drift allowing watermarks to be breached - */ - unsigned long percpu_drift_mark; - - /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -332,40 +335,26 @@ struct zone { * on the higher zones). This array is recalculated at runtime if the * sysctl_lowmem_reserve_ratio sysctl changes. */ - unsigned long lowmem_reserve[MAX_NR_ZONES]; - - /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. - */ - unsigned long dirty_balance_reserve; + long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; +#endif + /* - * zone reclaim becomes active if more unmapped pages exist. + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this zone's LRU. Maintained by the pageout code. */ - unsigned long min_unmapped_pages; - unsigned long min_slab_pages; -#endif + unsigned int inactive_ratio; + + struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; + /* - * free areas of different sizes + * This is a per-zone reserve of pages that should not be + * considered dirtyable memory. */ - spinlock_t lock; -#if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* Set to true when the PG_migrate_skip bits should be cleared */ - bool compact_blockskip_flush; - - /* pfns where compaction scanners should start */ - unsigned long compact_cached_free_pfn; - unsigned long compact_cached_migrate_pfn; -#endif -#ifdef CONFIG_MEMORY_HOTPLUG - /* see spanned/present_pages for more description */ - seqlock_t span_seqlock; -#endif - struct free_area free_area[MAX_ORDER]; + unsigned long dirty_balance_reserve; #ifndef CONFIG_SPARSEMEM /* @@ -375,71 +364,14 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_COMPACTION - /* - * On compaction failure, 1<<compact_defer_shift compactions - * are skipped before trying again. The number attempted since - * last failure is tracked with compact_considered. - */ - unsigned int compact_considered; - unsigned int compact_defer_shift; - int compact_order_failed; -#endif - - ZONE_PADDING(_pad1_) - - /* Fields commonly accessed by the page reclaim scanner */ - spinlock_t lru_lock; - struct lruvec lruvec; - - unsigned long pages_scanned; /* since last reclaim */ - unsigned long flags; /* zone flags, see below */ - - /* Zone statistics */ - atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - - /* - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on - * this zone's LRU. Maintained by the pageout code. - */ - unsigned int inactive_ratio; - - - ZONE_PADDING(_pad2_) - /* Rarely used or read-mostly fields */ - +#ifdef CONFIG_NUMA /* - * wait_table -- the array holding the hash table - * wait_table_hash_nr_entries -- the size of the hash table array - * wait_table_bits -- wait_table_size == (1 << wait_table_bits) - * - * The purpose of all these is to keep track of the people - * waiting for a page to become available and make them - * runnable again when possible. The trouble is that this - * consumes a lot of space, especially when so few things - * wait on pages at a given time. So instead of using - * per-page waitqueues, we use a waitqueue hash table. - * - * The bucket discipline is to sleep on the same queue when - * colliding and wake all in that wait queue when removing. - * When something wakes, it must check to be sure its page is - * truly available, a la thundering herd. The cost of a - * collision is great, but given the expected load of the - * table, they should be so rare as to be outweighed by the - * benefits from the saved space. - * - * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the - * primary users of these fields, and in mm/page_alloc.c - * free_area_init_core() performs the initialization of them. + * zone reclaim becomes active if more unmapped pages exist. */ - wait_queue_head_t * wait_table; - unsigned long wait_table_hash_nr_entries; - unsigned long wait_table_bits; + unsigned long min_unmapped_pages; + unsigned long min_slab_pages; +#endif /* CONFIG_NUMA */ - /* - * Discontig memory support fields. - */ - struct pglist_data *zone_pgdat; /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -485,14 +417,103 @@ struct zone { * adjust_managed_page_count() should be used instead of directly * touching zone->managed_pages and totalram_pages. */ + unsigned long managed_pages; unsigned long spanned_pages; unsigned long present_pages; - unsigned long managed_pages; + + const char *name; /* - * rarely used fields: + * Number of MIGRATE_RESEVE page block. To maintain for just + * optimization. Protected by zone->lock. */ - const char *name; + int nr_migrate_reserve_block; + +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif + + /* + * wait_table -- the array holding the hash table + * wait_table_hash_nr_entries -- the size of the hash table array + * wait_table_bits -- wait_table_size == (1 << wait_table_bits) + * + * The purpose of all these is to keep track of the people + * waiting for a page to become available and make them + * runnable again when possible. The trouble is that this + * consumes a lot of space, especially when so few things + * wait on pages at a given time. So instead of using + * per-page waitqueues, we use a waitqueue hash table. + * + * The bucket discipline is to sleep on the same queue when + * colliding and wake all in that wait queue when removing. + * When something wakes, it must check to be sure its page is + * truly available, a la thundering herd. The cost of a + * collision is great, but given the expected load of the + * table, they should be so rare as to be outweighed by the + * benefits from the saved space. + * + * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the + * primary users of these fields, and in mm/page_alloc.c + * free_area_init_core() performs the initialization of them. + */ + wait_queue_head_t *wait_table; + unsigned long wait_table_hash_nr_entries; + unsigned long wait_table_bits; + + ZONE_PADDING(_pad1_) + + /* Write-intensive fields used from the page allocator */ + spinlock_t lock; + + /* free areas of different sizes */ + struct free_area free_area[MAX_ORDER]; + + /* zone flags, see below */ + unsigned long flags; + + ZONE_PADDING(_pad2_) + + /* Write-intensive fields used by page reclaim */ + + /* Fields commonly accessed by the page reclaim scanner */ + spinlock_t lru_lock; + struct lruvec lruvec; + + /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* pfn where compaction free scanner should start */ + unsigned long compact_cached_free_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; +#endif + +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<<compact_defer_shift compactions + * are skipped before trying again. The number attempted since + * last failure is tracked with compact_considered. + */ + unsigned int compact_considered; + unsigned int compact_defer_shift; + int compact_order_failed; +#endif + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* Set to true when the PG_migrate_skip bits should be cleared */ + bool compact_blockskip_flush; +#endif + + ZONE_PADDING(_pad3_) + /* Zone statistics */ + atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; typedef enum { @@ -508,6 +529,7 @@ typedef enum { ZONE_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -545,6 +567,11 @@ static inline int zone_is_reclaim_locked(const struct zone *zone) return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); } +static inline int zone_is_fair_depleted(const struct zone *zone) +{ + return test_bit(ZONE_FAIR_DEPLETED, &zone->flags); +} + static inline int zone_is_oom_locked(const struct zone *zone) { return test_bit(ZONE_OOM_LOCKED, &zone->flags); @@ -799,10 +826,10 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) extern struct mutex zonelists_mutex; void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); +bool zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, diff --git a/include/linux/module.h b/include/linux/module.h index 05f2447..54aef1b 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -143,7 +143,7 @@ extern const struct gtype##_id __mod_##gtype##_table \ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) #define MODULE_DEVICE_TABLE(type,name) \ - MODULE_GENERIC_TABLE(type##_device,name) + MODULE_GENERIC_TABLE(type##__##name##_device, name) /* Version of form [<epoch>:]<version>[-<extra-version>]. Or for CVS/RCS ID version, everything but the number is stripped. diff --git a/include/linux/mount.h b/include/linux/mount.h index 38cd98f..22e5b96 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -42,11 +42,18 @@ struct mnt_namespace; * flag, consider how it interacts with shared mounts. */ #define MNT_SHARED_MASK (MNT_UNBINDABLE) -#define MNT_PROPAGATION_MASK (MNT_SHARED | MNT_UNBINDABLE) +#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ + | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ + | MNT_READONLY) +#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL 0x4000 +#define MNT_LOCK_ATIME 0x040000 +#define MNT_LOCK_NOEXEC 0x080000 +#define MNT_LOCK_NOSUID 0x100000 +#define MNT_LOCK_NODEV 0x200000 #define MNT_LOCK_READONLY 0x400000 #define MNT_LOCKED 0x800000 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9963e18..30e0620 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2898,6 +2898,20 @@ extern const char *netdev_drivername(const struct net_device *dev); extern void linkwatch_run_queue(void); +static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, + netdev_features_t f2) +{ + if (f1 & NETIF_F_GEN_CSUM) + f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if (f2 & NETIF_F_GEN_CSUM) + f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 &= f2; + if (f1 & NETIF_F_GEN_CSUM) + f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + + return f1; +} + static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) { diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 7a6c396..8b50a62 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -16,9 +16,10 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) } enum netlink_skb_flags { - NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ - NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ - NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ + NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ + NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */ }; struct netlink_skb_parms { @@ -171,4 +172,11 @@ extern int netlink_add_tap(struct netlink_tap *nt); extern int __netlink_remove_tap(struct netlink_tap *nt); extern int netlink_remove_tap(struct netlink_tap *nt); +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *ns, int cap); +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *ns, int cap); +bool netlink_capable(const struct sk_buff *skb, int cap); +bool netlink_net_capable(const struct sk_buff *skb, int cap); + #endif /* __LINUX_NETLINK_H */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2b30701..715671e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1223,11 +1223,22 @@ struct nfs41_free_stateid_res { unsigned int status; }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ + kfree(cinfo->buckets); +} + #else struct pnfs_ds_commit_info { }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ +} + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; diff --git a/include/linux/of.h b/include/linux/of.h index d27359a..da95cf0 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -263,14 +263,12 @@ extern int of_property_read_u64(const struct device_node *np, extern int of_property_read_string(struct device_node *np, const char *propname, const char **out_string); -extern int of_property_read_string_index(struct device_node *np, - const char *propname, - int index, const char **output); extern int of_property_match_string(struct device_node *np, const char *propname, const char *string); -extern int of_property_count_strings(struct device_node *np, - const char *propname); +extern int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); @@ -450,15 +448,9 @@ static inline int of_property_read_string(struct device_node *np, return -ENOSYS; } -static inline int of_property_read_string_index(struct device_node *np, - const char *propname, int index, - const char **out_string) -{ - return -ENOSYS; -} - -static inline int of_property_count_strings(struct device_node *np, - const char *propname) +static inline int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index) { return -ENOSYS; } @@ -560,6 +552,70 @@ static inline int of_node_to_nid(struct device_node *np) #endif /** + * of_property_read_string_array() - Read an array of strings from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * + * Search for a property in a device tree node and retrieve a list of + * terminated string values (pointer to data, not a copy) in that property. + * + * If @out_strs is NULL, the number of strings in the property is returned. + */ +static inline int of_property_read_string_array(struct device_node *np, + const char *propname, const char **out_strs, + size_t sz) +{ + return of_property_read_string_helper(np, propname, out_strs, sz, 0); +} + +/** + * of_property_count_strings() - Find and return the number of strings from a + * multiple strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device tree node and retrieve the number of null + * terminated string contain in it. Returns the number of strings on + * success, -EINVAL if the property does not exist, -ENODATA if property + * does not have a value, and -EILSEQ if the string is not null-terminated + * within the length of the property data. + */ +static inline int of_property_count_strings(struct device_node *np, + const char *propname) +{ + return of_property_read_string_helper(np, propname, NULL, 0, 0); +} + +/** + * of_property_read_string_index() - Find and read a string from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @index: index of the string in the list of strings + * @out_string: pointer to null terminated return string, modified only if + * return value is 0. + * + * Search for a property in a device tree node and retrieve a null + * terminated string value (pointer to data, not a copy) in the list of strings + * contained in that property. + * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if + * property does not have a value, and -EILSEQ if the string is not + * null-terminated within the length of the property data. + * + * The out_string pointer is modified only if a valid string can be decoded. + */ +static inline int of_property_read_string_index(struct device_node *np, + const char *propname, + int index, const char **output) +{ + int rc = of_property_read_string_helper(np, propname, output, 1, index); + return rc < 0 ? rc : 0; +} + +/** * of_property_read_bool - Findfrom a property * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. diff --git a/include/linux/oom.h b/include/linux/oom.h index da60007..297cda5 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p) extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); + +extern int oom_kills_count(void); +extern void note_oom_kill(void); extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, nodemask_t *nodemask, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6d53675..2284ea6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,6 +198,7 @@ struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) + __SETPAGEFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) @@ -208,6 +209,7 @@ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) + __SETPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobFree, slob_free) @@ -228,9 +230,9 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) PAGEFLAG(MappedToDisk, mappedtodisk) -/* PG_readahead is only used for file reads; PG_reclaim is only for writes */ +/* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) -PAGEFLAG(Readahead, reclaim) /* Reminder to do async read-ahead */ +PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim) #ifdef CONFIG_HIGHMEM /* @@ -317,13 +319,23 @@ CLEARPAGEFLAG(Uptodate, uptodate) 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); +int __test_set_page_writeback(struct page *page, bool keep_write); + +#define test_set_page_writeback(page) \ + __test_set_page_writeback(page, false) +#define test_set_page_writeback_keepwrite(page) \ + __test_set_page_writeback(page, true) static inline void set_page_writeback(struct page *page) { test_set_page_writeback(page); } +static inline void set_page_writeback_keepwrite(struct page *page) +{ + test_set_page_writeback_keepwrite(page); +} + #ifdef CONFIG_PAGEFLAGS_EXTENDED /* * System with lots of page flags available. This allows separate diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 2ee8cd2..2baeee1 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -30,9 +30,12 @@ enum pageblock_bits { PB_migrate, PB_migrate_end = PB_migrate + 3 - 1, /* 3 bits required for migrate types */ -#ifdef CONFIG_COMPACTION PB_migrate_skip,/* If set the block is skipped by compaction */ -#endif /* CONFIG_COMPACTION */ + + /* + * Assume the bits will always align on a word. If this assumption + * changes then get/set pageblock needs updating. + */ NR_PAGEBLOCK_BITS }; @@ -62,11 +65,26 @@ extern int pageblock_order; /* Forward declaration */ struct page; +unsigned long get_pfnblock_flags_mask(struct page *page, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask); + +void set_pfnblock_flags_mask(struct page *page, + unsigned long flags, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask); + /* Declarations for getting and setting flags. See mm/page_alloc.c */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx); -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx); +#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) +#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \ + set_pfnblock_flags_mask(page, flags, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e3dea75..bf944e8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -99,7 +99,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_get(page) get_page(page) #define page_cache_release(page) put_page(page) -void release_pages(struct page **pages, int nr, int cold); +void release_pages(struct page **pages, int nr, bool cold); /* * speculatively take a reference to a page. @@ -243,12 +243,116 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x) typedef int filler_t(void *, struct page *); -extern struct page * find_get_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_lock_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); + +#define FGP_ACCESSED 0x00000001 +#define FGP_LOCK 0x00000002 +#define FGP_CREAT 0x00000004 +#define FGP_WRITE 0x00000008 +#define FGP_NOFS 0x00000010 +#define FGP_NOWAIT 0x00000020 + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask); + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct page *find_get_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, 0, 0); +} + +static inline struct page *find_get_page_flags(struct address_space *mapping, + pgoff_t offset, int fgp_flags) +{ + return pagecache_get_page(mapping, offset, fgp_flags, 0); +} + +/** + * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +static inline struct page *find_lock_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, FGP_LOCK, 0); +} + +/** + * find_or_create_page - locate or add a pagecache page + * @mapping: the page's address_space + * @index: the page's index into the mapping + * @gfp_mask: page allocation mode + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. + * + * On memory exhaustion, %NULL is returned. + * + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! + */ +static inline struct page *find_or_create_page(struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return pagecache_get_page(mapping, offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT, + gfp_mask); +} + +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * + * Same as grab_cache_page(), but do not wait if the page is unavailable. + * This is intended for speculative data generators, where the data can + * be regenerated if the page couldn't be grabbed. This routine should + * be safe to call while holding the lock for another page. + * + * Clear __GFP_FS when allocating the page to avoid recursion into the fs + * and deadlock against the caller's locked page. + */ +static inline struct page *grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping)); +} + +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, @@ -268,10 +372,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * grab_cache_page_nowait(struct address_space *mapping, - pgoff_t index); -extern struct page * read_cache_page_async(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, @@ -279,14 +379,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping, extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); -static inline struct page *read_mapping_page_async( - struct address_space *mapping, - pgoff_t index, void *data) -{ - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return read_cache_page_async(mapping, index, filler, data); -} - static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index e4dbfab..b45d391 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -22,6 +22,11 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_entries, + pgoff_t *indices); +void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, diff --git a/include/linux/pci.h b/include/linux/pci.h index c587034..825d604 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -323,6 +323,7 @@ struct pci_dev { unsigned int is_added:1; unsigned int is_busmaster:1; /* device is busmaster */ unsigned int no_msi:1; /* device may not use msi */ + unsigned int no_64bit_msi:1; /* device may only use 32-bit MSIs */ unsigned int block_cfg_access:1; /* config space access is blocked */ unsigned int broken_parity_status:1; /* Device generates false positive parity */ unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */ @@ -478,6 +479,15 @@ static inline bool pci_is_root_bus(struct pci_bus *pbus) return !(pbus->parent); } +static inline struct pci_dev *pci_upstream_bridge(struct pci_dev *dev) +{ + dev = pci_physfn(dev); + if (pci_is_root_bus(dev->bus)) + return NULL; + + return dev->bus->self; +} + #ifdef CONFIG_PCI_MSI static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 97fbecd..057c1d8 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2551,6 +2551,7 @@ #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 #define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 95961f0..0afb48f 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -110,7 +110,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref) pcpu_count = ACCESS_ONCE(ref->pcpu_count); if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) - __this_cpu_inc(*pcpu_count); + this_cpu_inc(*pcpu_count); else atomic_inc(&ref->count); @@ -139,7 +139,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) pcpu_count = ACCESS_ONCE(ref->pcpu_count); if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) { - __this_cpu_inc(*pcpu_count); + this_cpu_inc(*pcpu_count); ret = true; } @@ -164,7 +164,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref) pcpu_count = ACCESS_ONCE(ref->pcpu_count); if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) - __this_cpu_dec(*pcpu_count); + this_cpu_dec(*pcpu_count); else if (unlikely(atomic_dec_and_test(&ref->count))) ref->release(ref); diff --git a/include/linux/plist.h b/include/linux/plist.h index aa0fb39..8b6c970 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -98,6 +98,13 @@ struct plist_node { } /** + * PLIST_HEAD - declare and init plist_head + * @head: name for struct plist_head variable + */ +#define PLIST_HEAD(head) \ + struct plist_head head = PLIST_HEAD_INIT(head) + +/** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name * @__prio: initial node priority @@ -134,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio) extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); +extern void plist_requeue(struct plist_node *node, struct plist_head *head); + /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter @@ -143,6 +152,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, node_list) /** + * plist_for_each_continue - continue iteration over the plist + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * + * Continue to iterate over plist, continuing after the current position. + */ +#define plist_for_each_continue(pos, head) \ + list_for_each_entry_continue(pos, &(head)->node_list, node_list) + +/** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -163,6 +182,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** + * plist_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * @m: the name of the list_struct within the struct + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define plist_for_each_entry_continue(pos, head, m) \ + list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) + +/** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -229,6 +260,20 @@ static inline int plist_node_empty(const struct plist_node *node) #endif /** + * plist_next - get the next entry in list + * @pos: the type * to cursor + */ +#define plist_next(pos) \ + list_next_entry(pos, node_list) + +/** + * plist_prev - get the prev entry in list + * @pos: the type * to cursor + */ +#define plist_prev(pos) \ + list_prev_entry(pos, node_list) + +/** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer * diff --git a/include/linux/printk.h b/include/linux/printk.h index c262485..a2d18be 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -126,9 +126,9 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* - * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_sched(const char *fmt, ...); +__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -162,7 +162,7 @@ int printk(const char *s, ...) return 0; } static inline __printf(1, 2) __cold -int printk_sched(const char *s, ...) +int printk_deferred(const char *s, ...) { return 0; } diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9974975..4af3fdc 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -53,7 +53,8 @@ struct persistent_ram_zone { }; struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, struct persistent_ram_ecc_info *ecc_info); + u32 sig, struct persistent_ram_ecc_info *ecc_info, + unsigned int memtype); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); @@ -76,6 +77,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, struct ramoops_platform_data { unsigned long mem_size; unsigned long mem_address; + unsigned int mem_type; unsigned long record_size; unsigned long console_size; unsigned long ftrace_size; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 07d0df6..cc79eff 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -5,6 +5,7 @@ #include <linux/sched.h> /* For struct task_struct. */ #include <linux/err.h> /* for IS_ERR_VALUE */ #include <linux/bug.h> /* For BUG_ON. */ +#include <linux/pid_namespace.h> /* For task_active_pid_ns. */ #include <uapi/linux/ptrace.h> /* @@ -129,6 +130,37 @@ static inline void ptrace_event(int event, unsigned long message) } /** + * ptrace_event_pid - possibly stop for a ptrace event notification + * @event: %PTRACE_EVENT_* value to report + * @pid: process identifier for %PTRACE_GETEVENTMSG to return + * + * Check whether @event is enabled and, if so, report @event and @pid + * to the ptrace parent. @pid is reported as the pid_t seen from the + * the ptrace parent's pid namespace. + * + * Called without locks. + */ +static inline void ptrace_event_pid(int event, struct pid *pid) +{ + /* + * FIXME: There's a potential race if a ptracer in a different pid + * namespace than parent attaches between computing message below and + * when we acquire tasklist_lock in ptrace_stop(). If this happens, + * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG. + */ + unsigned long message = 0; + struct pid_namespace *ns; + + rcu_read_lock(); + ns = task_active_pid_ns(rcu_dereference(current->parent)); + if (ns) + message = pid_nr_ns(pid, ns); + rcu_read_unlock(); + + ptrace_event(event, message); +} + +/** * ptrace_init_task - initialize ptrace state for a new child * @child: new child task * @ptrace: true if child should be ptrace'd by parent's tracer @@ -302,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, * calling arch_ptrace_stop() when it would be superfluous. For example, * if the thread has not been back to user mode since the last stop, the * thread state might indicate that nothing needs to be done. + * + * This is guaranteed to be invoked once before a task stops for ptrace and + * may include arch-specific operations necessary prior to a ptrace stop. */ #define arch_ptrace_stop_needed(code, info) (0) #endif diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 6965fe3..1d3eee5 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -46,6 +46,14 @@ void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); void dquot_initialize(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); +static inline struct dquot *dqgrab(struct dquot *dquot) +{ + /* Make sure someone else has active reference to dquot */ + WARN_ON_ONCE(!atomic_read(&dquot->dq_count)); + WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); + atomic_inc(&dquot->dq_count); + return dquot; +} void dqput(struct dquot *dquot); int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 5b6d5b2..ab8263e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item) int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, @@ -226,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); #ifndef CONFIG_PREEMPT_RT_FULL int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index d69cf63..49a4d6f 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) -void ring_buffer_wait(struct ring_buffer *buffer, int cpu); +int ring_buffer_wait(struct ring_buffer *buffer, int cpu); int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index f28544b..321f4ec 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -4,6 +4,7 @@ #include <linux/mutex.h> #include <linux/netdevice.h> +#include <linux/wait.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -22,6 +23,10 @@ extern void rtnl_lock(void); extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); + +extern wait_queue_head_t netdev_unregistering_wq; +extern struct mutex net_mutex; + #ifdef CONFIG_PROVE_LOCKING extern int lockdep_rtnl_is_held(void); #endif /* #ifdef CONFIG_PROVE_LOCKING */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 625a41f..3ce814c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,6 +65,10 @@ struct fs_struct; struct perf_event_context; struct blk_plug; +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) + /* * List of flags we want to share for kernel threads, * if only because they are not used by them anyway. @@ -469,6 +473,7 @@ struct signal_struct { atomic_t sigcnt; atomic_t live; int nr_threads; + struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -1098,6 +1103,9 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif + /* per-thread vma caching */ + u32 vmacache_seqnum; + struct vm_area_struct *vmacache[VMACACHE_SIZE]; #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif @@ -1154,6 +1162,7 @@ struct task_struct { /* PID/PID hash table linkage. */ struct pid_link pids[PIDTYPE_MAX]; struct list_head thread_group; + struct list_head thread_node; struct completion *vfork_done; /* for vfork() */ int __user *set_child_tid; /* CLONE_CHILD_SETTID */ @@ -1547,6 +1556,24 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } +static inline int pid_alive(const struct task_struct *p); +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1586,7 +1613,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) * * Return: 1 if the process is alive. 0 otherwise. */ -static inline int pid_alive(struct task_struct *p) +static inline int pid_alive(const struct task_struct *p) { return p->pids[PIDTYPE_PID].pid != NULL; } @@ -1721,11 +1748,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags + * __GFP_FS is also cleared as it implies __GFP_IO. + */ static inline gfp_t memalloc_noio_flags(gfp_t flags) { if (unlikely(current->flags & PF_MEMALLOC_NOIO)) - flags &= ~__GFP_IO; + flags &= ~(__GFP_IO | __GFP_FS); return flags; } @@ -2240,6 +2269,16 @@ extern bool current_is_single_threaded(void); #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) +#define __for_each_thread(signal, t) \ + list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) + +#define for_each_thread(p, t) \ + __for_each_thread((p)->signal, t) + +/* Careful: this is a double loop, 'break' won't work as expected. */ +#define for_each_process_thread(p, t) \ + for_each_process(p) for_each_thread(p, t) + static inline int get_nr_threads(struct task_struct *tsk) { return tsk->signal->nr_threads; diff --git a/include/linux/serio.h b/include/linux/serio.h index 36aac73..9f779c7 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -23,6 +23,7 @@ struct serio { char name[32]; char phys[32]; + char firmware_id[128]; bool manual_bind; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 30aa0dc..deb4960 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -49,6 +49,7 @@ extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7406b93..e13de0b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2403,6 +2403,7 @@ extern struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); +struct sk_buff *skb_vlan_untag(struct sk_buff *skb); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 54f91d3..46cca4c 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -23,7 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie); void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); #endif diff --git a/include/linux/string.h b/include/linux/string.h index ac889c5..0ed878d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -129,7 +129,7 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); + const void *from, size_t available); /** * strstarts - does @str start with @prefix? @@ -141,7 +141,8 @@ static inline bool strstarts(const char *str, const char *prefix) return strncmp(str, prefix, strlen(prefix)) == 0; } -extern size_t memweight(const void *ptr, size_t bytes); +size_t memweight(const void *ptr, size_t bytes); +void memzero_explicit(void *s, size_t count); /** * kbasename - return the last part of a pathname. diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index b05963f..f5bfb1a 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -32,6 +32,7 @@ struct svc_xprt_class { struct svc_xprt_ops *xcl_ops; struct list_head xcl_list; u32 xcl_max_payload; + int xcl_ident; }; /* diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 62fd1b7..947009e 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -56,6 +56,7 @@ int svc_recv(struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); +bool svc_alien_sock(struct net *net, int fd); int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, const size_t len); void svc_init_xprt_sock(void); diff --git a/include/linux/swap.h b/include/linux/swap.h index 46ba0c6..241bf09 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,8 +214,9 @@ struct percpu_cluster { struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ + struct plist_node list; /* entry in swap_active_head */ + struct plist_node avail_list; /* entry in swap_avail_head */ signed char type; /* strange name for an index */ - signed char next; /* next type on the swap list */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ @@ -255,11 +256,6 @@ struct swap_info_struct { struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ }; -struct swap_list_t { - int head; /* head of priority-ordered swapfile list */ - int next; /* swapfile to be used next */ -}; - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; @@ -272,12 +268,14 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void __lru_cache_add(struct page *); extern void lru_cache_add(struct page *); +extern void lru_cache_add_anon(struct page *page); +extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); +extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); @@ -287,22 +285,6 @@ extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); -/** - * lru_cache_add: add a page to the page lists - * @page: the page to add - */ -static inline void lru_cache_add_anon(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - -static inline void lru_cache_add_file(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); @@ -460,7 +442,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #define free_page_and_swap_cache(page) \ page_cache_release(page) #define free_pages_and_swap_cache(pages, nr) \ - release_pages((pages), (nr), 0); + release_pages((pages), (nr), false); static inline void show_swap_cache_info(void) { diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e282624..388293a 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,7 +6,7 @@ * want to expose them to the dozens of source files that include swap.h */ extern spinlock_t swap_lock; -extern struct swap_list_t swap_list; +extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); diff --git a/include/linux/time.h b/include/linux/time.h index d5d229b..7d532a3 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -173,6 +173,19 @@ extern void getboottime(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); extern void get_monotonic_boottime(struct timespec *ts); +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + extern struct timespec timespec_trunc(struct timespec t, unsigned gran); extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 52f944d..3fb4288 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -30,4 +30,24 @@ descriptor */ #define USB_QUIRK_DELAY_INIT 0x00000040 +/* + * For high speed and super speed interupt endpoints, the USB 2.0 and + * USB 3.0 spec require the interval in microframes + * (1 microframe = 125 microseconds) to be calculated as + * interval = 2 ^ (bInterval-1). + * + * Devices with this quirk report their bInterval as the result of this + * calculation instead of the exponent variable used in the calculation. + */ +#define USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL 0x00000080 + +/* device generates spurious wakeup, ignore remote wakeup capability */ +#define USB_QUIRK_IGNORE_REMOTE_WAKEUP 0x00000200 + +/* device generates spurious wakeup, ignore remote wakeup capability */ +#define USB_QUIRK_IGNORE_REMOTE_WAKEUP 0x00000200 + +/* device can't handle device_qualifier descriptor requests */ +#define USB_QUIRK_DEVICE_QUALIFIER 0x00000100 + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4db2985..67c1108 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -17,6 +17,10 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */ } extent[UID_GID_MAP_MAX_EXTENTS]; }; +#define USERNS_SETGROUPS_ALLOWED 1UL + +#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -27,6 +31,7 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; + unsigned long flags; }; extern struct user_namespace init_user_ns; @@ -57,6 +62,9 @@ extern struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); +extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); +extern int proc_setgroups_show(struct seq_file *m, void *v); +extern bool userns_may_setgroups(const struct user_namespace *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -81,6 +89,10 @@ static inline void put_user_ns(struct user_namespace *ns) { } +static inline bool userns_may_setgroups(const struct user_namespace *ns) +{ + return true; +} #endif #endif /* _LINUX_USER_H */ diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 502073a..b483abd 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -64,6 +64,7 @@ int vga_switcheroo_get_client_state(struct pci_dev *dev); void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev); int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain); #else @@ -82,6 +83,7 @@ static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } +static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {} static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } #endif diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index c557c6d..3a712e2 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif +#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, +#endif /* CONFIG_DEBUG_TLBFLUSH */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h new file mode 100644 index 0000000..c3fa0fd4 --- /dev/null +++ b/include/linux/vmacache.h @@ -0,0 +1,38 @@ +#ifndef __LINUX_VMACACHE_H +#define __LINUX_VMACACHE_H + +#include <linux/sched.h> +#include <linux/mm.h> + +/* + * Hash based on the page number. Provides a good hit rate for + * workloads with good locality and those with random accesses as well. + */ +#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK) + +static inline void vmacache_flush(struct task_struct *tsk) +{ + memset(tsk->vmacache, 0, sizeof(tsk->vmacache)); +} + +extern void vmacache_flush_all(struct mm_struct *mm); +extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); +extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, + unsigned long addr); + +#ifndef CONFIG_MMU +extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end); +#endif + +static inline void vmacache_invalidate(struct mm_struct *mm) +{ + mm->vmacache_seqnum++; + + /* deal with overflows */ + if (unlikely(mm->vmacache_seqnum == 0)) + vmacache_flush_all(mm); +} + +#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 1ea2fd5..fe37043 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -87,6 +87,14 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_DEBUG_TLBFLUSH +#define count_vm_tlb_event(x) count_vm_event(x) +#define count_vm_tlb_events(x, y) count_vm_events(x, y) +#else +#define count_vm_tlb_event(x) do {} while (0) +#define count_vm_tlb_events(x, y) do { (void)(y); } while (0) +#endif + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 594521b..eff358e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -455,7 +455,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \ 1, (name)) #define create_singlethread_workqueue(name) \ - alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name)) + alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); |