diff options
Diffstat (limited to 'include/linux')
78 files changed, 2227 insertions, 837 deletions
diff --git a/include/linux/asn1.h b/include/linux/asn1.h index 5c3f4e4..eed6982 100644 --- a/include/linux/asn1.h +++ b/include/linux/asn1.h @@ -64,4 +64,6 @@ enum asn1_tag { ASN1_LONG_TAG = 31 /* Long form tag */ }; +#define ASN1_INDEFINITE_LENGTH 0x80 + #endif /* _LINUX_ASN1_H */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 238521a..2a9a9ab 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -18,7 +18,6 @@ #include <linux/writeback.h> #include <linux/atomic.h> #include <linux/sysctl.h> -#include <linux/mutex.h> struct page; struct device; @@ -106,9 +105,6 @@ struct backing_dev_info { struct timer_list laptop_mode_wb_timer; - cpumask_t *flusher_cpumask; /* used for writeback thread scheduling */ - struct mutex flusher_cpumask_lock; - #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 5ffc6dd..da9a082 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -134,4 +134,14 @@ struct generic_bl_info { void (*kick_battery)(void); }; +#ifdef CONFIG_OF +struct backlight_device *of_find_backlight_by_node(struct device_node *node); +#else +static inline struct backlight_device * +of_find_backlight_by_node(struct device_node *node) +{ + return NULL; +} +#endif + #endif diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 93b1e09..e0ce311 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -350,6 +350,7 @@ extern void bcma_core_set_clockmode(struct bcma_device *core, enum bcma_clkmode clkmode); extern void bcma_core_pll_ctl(struct bcma_device *core, u32 req, u32 status, bool on); +extern u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset); #define BCMA_DMA_TRANSLATION_MASK 0xC0000000 #define BCMA_DMA_TRANSLATION_NONE 0x00000000 #define BCMA_DMA_TRANSLATION_DMA32_CMT 0x40000000 /* Client Mode Translation for 32-bit DMA */ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 2630c9b..a4c2b56 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -54,8 +54,6 @@ struct linux_binprm { #define BINPRM_FLAGS_EXECFD_BIT 1 #define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT) -#define BINPRM_MAX_RECURSION 4 - /* Function parameter for binfmt->coredump */ struct coredump_params { siginfo_t *siginfo; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index acb4f7b..f94bc83 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1188,14 +1188,25 @@ static inline int queue_discard_alignment(struct request_queue *q) static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { - sector_t alignment = sector << 9; - alignment = sector_div(alignment, lim->discard_granularity); + unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; - alignment = lim->discard_granularity + lim->discard_alignment - alignment; - return sector_div(alignment, lim->discard_granularity); + /* Why are these in bytes, not sectors? */ + alignment = lim->discard_alignment >> 9; + granularity = lim->discard_granularity >> 9; + if (!granularity) + return 0; + + /* Offset of the partition start in 'granularity' sectors */ + offset = sector_div(sector, granularity); + + /* And why do we do this modulus *again* in blkdev_issue_discard()? */ + offset = (granularity + alignment - offset) % granularity; + + /* Turn it back into bytes, gaah */ + return offset << 9; } static inline int bdev_discard_alignment(struct block_device *bdev) diff --git a/include/linux/compat.h b/include/linux/compat.h index 784ebfe..e4920bd 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -588,6 +588,9 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); +asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, + struct compat_timespec __user *interval); + #else #define is_compat_task() (0) diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 412bc6c..662fd1b 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -31,6 +31,8 @@ #define __linktime_error(message) __attribute__((__error__(message))) +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + #if __GNUC_MINOR__ >= 5 /* * Mark a position in code as unreachable. This can be used to @@ -63,3 +65,13 @@ #define __compiletime_warning(message) __attribute__((warning(message))) #define __compiletime_error(message) __attribute__((error(message))) #endif + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#if __GNUC_MINOR__ >= 4 +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#endif +#if __GNUC_MINOR__ >= 8 || (defined(__powerpc__) && __GNUC_MINOR__ >= 6) +#define __HAVE_BUILTIN_BSWAP16__ +#endif +#endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index d8e636e..973ce10 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -29,3 +29,10 @@ #endif #define uninitialized_var(x) x + +#ifndef __HAVE_BUILTIN_BSWAP16__ +/* icc has this, but it's called _bswap16 */ +#define __HAVE_BUILTIN_BSWAP16__ +#define __builtin_bswap16 _bswap16 +#endif + diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f430e41..dd852b7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -10,6 +10,7 @@ # define __force __attribute__((force)) # define __nocast __attribute__((nocast)) # define __iomem __attribute__((noderef, address_space(2))) +# define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) # define __releases(x) __attribute__((context(x,1,0))) # define __acquire(x) __context__(x,1) @@ -33,6 +34,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 # define __builtin_warning(x, y...) (1) +# define __must_hold(x) # define __acquires(x) # define __releases(x) # define __acquire(x) (void)0 @@ -42,6 +44,10 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __rcu #endif +/* Indirect macros required for expanded argument pasting, eg. __LINE__. */ +#define ___PASTE(a,b) a##b +#define __PASTE(a,b) ___PASTE(a,b) + #ifdef __KERNEL__ #ifdef __GNUC__ @@ -164,6 +170,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); (typeof(ptr)) (__ptr + (off)); }) #endif +/* Not-quite-unique ID. */ +#ifndef __UNIQUE_ID +# define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) +#endif + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/include/linux/cred.h b/include/linux/cred.h index 0142aac..abb2cd5 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -344,10 +344,8 @@ static inline void put_cred(const struct cred *_cred) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) -#define task_user_ns(task) (task_cred_xxx((task), user_ns)) #else #define current_user_ns() (&init_user_ns) -#define task_user_ns(task) (&init_user_ns) #endif diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index eb48f38..bd2e52c 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -156,7 +156,6 @@ static inline void get_dma_buf(struct dma_buf *dmabuf) get_file(dmabuf->file); } -#ifdef CONFIG_DMA_SHARED_BUFFER struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); void dma_buf_detach(struct dma_buf *dmabuf, @@ -184,103 +183,5 @@ int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); void *dma_buf_vmap(struct dma_buf *); void dma_buf_vunmap(struct dma_buf *, void *vaddr); -#else - -static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, - struct device *dev) -{ - return ERR_PTR(-ENODEV); -} - -static inline void dma_buf_detach(struct dma_buf *dmabuf, - struct dma_buf_attachment *dmabuf_attach) -{ - return; -} - -static inline struct dma_buf *dma_buf_export(void *priv, - const struct dma_buf_ops *ops, - size_t size, int flags) -{ - return ERR_PTR(-ENODEV); -} - -static inline int dma_buf_fd(struct dma_buf *dmabuf, int flags) -{ - return -ENODEV; -} - -static inline struct dma_buf *dma_buf_get(int fd) -{ - return ERR_PTR(-ENODEV); -} - -static inline void dma_buf_put(struct dma_buf *dmabuf) -{ - return; -} - -static inline struct sg_table *dma_buf_map_attachment( - struct dma_buf_attachment *attach, enum dma_data_direction write) -{ - return ERR_PTR(-ENODEV); -} - -static inline void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, - struct sg_table *sg, enum dma_data_direction dir) -{ - return; -} - -static inline int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, - size_t start, size_t len, - enum dma_data_direction dir) -{ - return -ENODEV; -} - -static inline void dma_buf_end_cpu_access(struct dma_buf *dmabuf, - size_t start, size_t len, - enum dma_data_direction dir) -{ -} - -static inline void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, - unsigned long pnum) -{ - return NULL; -} - -static inline void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, - unsigned long pnum, void *vaddr) -{ -} - -static inline void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long pnum) -{ - return NULL; -} - -static inline void dma_buf_kunmap(struct dma_buf *dmabuf, - unsigned long pnum, void *vaddr) -{ -} - -static inline int dma_buf_mmap(struct dma_buf *dmabuf, - struct vm_area_struct *vma, - unsigned long pgoff) -{ - return -ENODEV; -} - -static inline void *dma_buf_vmap(struct dma_buf *dmabuf) -{ - return NULL; -} - -static inline void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) -{ -} -#endif /* CONFIG_DMA_SHARED_BUFFER */ #endif /* __DMA_BUF_H__ */ diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 47e3d48..0c5a18e 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -51,12 +51,11 @@ #endif - extern const char *drbd_buildtag(void); -#define REL_VERSION "8.3.13" -#define API_VERSION 88 +#define REL_VERSION "8.4.2" +#define API_VERSION 1 #define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 96 +#define PRO_VERSION_MAX 101 enum drbd_io_error_p { @@ -66,7 +65,8 @@ enum drbd_io_error_p { }; enum drbd_fencing_p { - FP_DONT_CARE, + FP_NOT_AVAIL = -1, /* Not a policy */ + FP_DONT_CARE = 0, FP_RESOURCE, FP_STONITH }; @@ -102,6 +102,20 @@ enum drbd_on_congestion { OC_DISCONNECT, }; +enum drbd_read_balancing { + RB_PREFER_LOCAL, + RB_PREFER_REMOTE, + RB_ROUND_ROBIN, + RB_LEAST_PENDING, + RB_CONGESTED_REMOTE, + RB_32K_STRIPING, + RB_64K_STRIPING, + RB_128K_STRIPING, + RB_256K_STRIPING, + RB_512K_STRIPING, + RB_1M_STRIPING, +}; + /* KEEP the order, do not delete or insert. Only append. */ enum drbd_ret_code { ERR_CODE_BASE = 100, @@ -122,7 +136,7 @@ enum drbd_ret_code { ERR_AUTH_ALG = 120, ERR_AUTH_ALG_ND = 121, ERR_NOMEM = 122, - ERR_DISCARD = 123, + ERR_DISCARD_IMPOSSIBLE = 123, ERR_DISK_CONFIGURED = 124, ERR_NET_CONFIGURED = 125, ERR_MANDATORY_TAG = 126, @@ -130,8 +144,8 @@ enum drbd_ret_code { ERR_INTR = 129, /* EINTR */ ERR_RESIZE_RESYNC = 130, ERR_NO_PRIMARY = 131, - ERR_SYNC_AFTER = 132, - ERR_SYNC_AFTER_CYCLE = 133, + ERR_RESYNC_AFTER = 132, + ERR_RESYNC_AFTER_CYCLE = 133, ERR_PAUSE_IS_SET = 134, ERR_PAUSE_IS_CLEAR = 135, ERR_PACKET_NR = 137, @@ -155,6 +169,14 @@ enum drbd_ret_code { ERR_CONG_NOT_PROTO_A = 155, ERR_PIC_AFTER_DEP = 156, ERR_PIC_PEER_DEP = 157, + ERR_RES_NOT_KNOWN = 158, + ERR_RES_IN_USE = 159, + ERR_MINOR_CONFIGURED = 160, + ERR_MINOR_EXISTS = 161, + ERR_INVALID_REQUEST = 162, + ERR_NEED_APV_100 = 163, + ERR_NEED_ALLOW_TWO_PRI = 164, + ERR_MD_UNCLEAN = 165, /* insert new ones above this line */ AFTER_LAST_ERR_CODE @@ -296,7 +318,8 @@ enum drbd_state_rv { SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */ SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ - SS_AFTER_LAST_ERROR = -20, /* Keep this at bottom */ + SS_O_VOL_PEER_PRI = -20, + SS_AFTER_LAST_ERROR = -21, /* Keep this at bottom */ }; /* from drbd_strings.c */ @@ -313,7 +336,9 @@ extern const char *drbd_set_st_err_str(enum drbd_state_rv); #define MDF_FULL_SYNC (1 << 3) #define MDF_WAS_UP_TO_DATE (1 << 4) #define MDF_PEER_OUT_DATED (1 << 5) -#define MDF_CRASHED_PRIMARY (1 << 6) +#define MDF_CRASHED_PRIMARY (1 << 6) +#define MDF_AL_CLEAN (1 << 7) +#define MDF_AL_DISABLED (1 << 8) enum drbd_uuid_index { UI_CURRENT, @@ -333,37 +358,23 @@ enum drbd_timeout_flag { #define UUID_JUST_CREATED ((__u64)4) +/* magic numbers used in meta data and network packets */ #define DRBD_MAGIC 0x83740267 -#define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC) #define DRBD_MAGIC_BIG 0x835a -#define BE_DRBD_MAGIC_BIG __constant_cpu_to_be16(DRBD_MAGIC_BIG) +#define DRBD_MAGIC_100 0x8620ec20 + +#define DRBD_MD_MAGIC_07 (DRBD_MAGIC+3) +#define DRBD_MD_MAGIC_08 (DRBD_MAGIC+4) +#define DRBD_MD_MAGIC_84_UNCLEAN (DRBD_MAGIC+5) + + +/* how I came up with this magic? + * base64 decode "actlog==" ;) */ +#define DRBD_AL_MAGIC 0x69cb65a2 /* these are of type "int" */ #define DRBD_MD_INDEX_INTERNAL -1 #define DRBD_MD_INDEX_FLEX_EXT -2 #define DRBD_MD_INDEX_FLEX_INT -3 -/* Start of the new netlink/connector stuff */ - -#define DRBD_NL_CREATE_DEVICE 0x01 -#define DRBD_NL_SET_DEFAULTS 0x02 - - -/* For searching a vacant cn_idx value */ -#define CN_IDX_STEP 6977 - -struct drbd_nl_cfg_req { - int packet_type; - unsigned int drbd_minor; - int flags; - unsigned short tag_list[]; -}; - -struct drbd_nl_cfg_reply { - int packet_type; - unsigned int minor; - int ret_code; /* enum ret_code or set_st_err_t */ - unsigned short tag_list[]; /* only used with get_* calls */ -}; - #endif diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h new file mode 100644 index 0000000..d0d8fac --- /dev/null +++ b/include/linux/drbd_genl.h @@ -0,0 +1,378 @@ +/* + * General overview: + * full generic netlink message: + * |nlmsghdr|genlmsghdr|<payload> + * + * payload: + * |optional fixed size family header|<sequence of netlink attributes> + * + * sequence of netlink attributes: + * I chose to have all "top level" attributes NLA_NESTED, + * corresponding to some real struct. + * So we have a sequence of |tla, len|<nested nla sequence> + * + * nested nla sequence: + * may be empty, or contain a sequence of netlink attributes + * representing the struct fields. + * + * The tag number of any field (regardless of containing struct) + * will be available as T_ ## field_name, + * so you cannot have the same field name in two differnt structs. + * + * The tag numbers themselves are per struct, though, + * so should always begin at 1 (not 0, that is the special "NLA_UNSPEC" type, + * which we won't use here). + * The tag numbers are used as index in the respective nla_policy array. + * + * GENL_struct(tag_name, tag_number, struct name, struct fields) - struct and policy + * genl_magic_struct.h + * generates the struct declaration, + * generates an entry in the tla enum, + * genl_magic_func.h + * generates an entry in the static tla policy + * with .type = NLA_NESTED + * generates the static <struct_name>_nl_policy definition, + * and static conversion functions + * + * genl_magic_func.h + * + * GENL_mc_group(group) + * genl_magic_struct.h + * does nothing + * genl_magic_func.h + * defines and registers the mcast group, + * and provides a send helper + * + * GENL_notification(op_name, op_num, mcast_group, tla list) + * These are notifications to userspace. + * + * genl_magic_struct.h + * generates an entry in the genl_ops enum, + * genl_magic_func.h + * does nothing + * + * mcast group: the name of the mcast group this notification should be + * expected on + * tla list: the list of expected top level attributes, + * for documentation and sanity checking. + * + * GENL_op(op_name, op_num, flags and handler, tla list) - "genl operations" + * These are requests from userspace. + * + * _op and _notification share the same "number space", + * op_nr will be assigned to "genlmsghdr->cmd" + * + * genl_magic_struct.h + * generates an entry in the genl_ops enum, + * genl_magic_func.h + * generates an entry in the static genl_ops array, + * and static register/unregister functions to + * genl_register_family_with_ops(). + * + * flags and handler: + * GENL_op_init( .doit = x, .dumpit = y, .flags = something) + * GENL_doit(x) => .dumpit = NULL, .flags = GENL_ADMIN_PERM + * tla list: the list of expected top level attributes, + * for documentation and sanity checking. + */ + +/* + * STRUCTS + */ + +/* this is sent kernel -> userland on various error conditions, and contains + * informational textual info, which is supposedly human readable. + * The computer relevant return code is in the drbd_genlmsghdr. + */ +GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply, + /* "arbitrary" size strings, nla_policy.len = 0 */ + __str_field(1, DRBD_GENLA_F_MANDATORY, info_text, 0) +) + +/* Configuration requests typically need a context to operate on. + * Possible keys are device minor (fits in the drbd_genlmsghdr), + * the replication link (aka connection) name, + * and/or the replication group (aka resource) name, + * and the volume id within the resource. */ +GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context, + __u32_field(1, DRBD_GENLA_F_MANDATORY, ctx_volume) + __str_field(2, DRBD_GENLA_F_MANDATORY, ctx_resource_name, 128) + __bin_field(3, DRBD_GENLA_F_MANDATORY, ctx_my_addr, 128) + __bin_field(4, DRBD_GENLA_F_MANDATORY, ctx_peer_addr, 128) +) + +GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, + __str_field(1, DRBD_F_REQUIRED | DRBD_F_INVARIANT, backing_dev, 128) + __str_field(2, DRBD_F_REQUIRED | DRBD_F_INVARIANT, meta_dev, 128) + __s32_field(3, DRBD_F_REQUIRED | DRBD_F_INVARIANT, meta_dev_idx) + + /* use the resize command to try and change the disk_size */ + __u64_field(4, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT, disk_size) + /* we could change the max_bio_bvecs, + * but it won't propagate through the stack */ + __u32_field(5, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT, max_bio_bvecs) + + __u32_field_def(6, DRBD_GENLA_F_MANDATORY, on_io_error, DRBD_ON_IO_ERROR_DEF) + __u32_field_def(7, DRBD_GENLA_F_MANDATORY, fencing, DRBD_FENCING_DEF) + + __u32_field_def(8, DRBD_GENLA_F_MANDATORY, resync_rate, DRBD_RESYNC_RATE_DEF) + __s32_field_def(9, DRBD_GENLA_F_MANDATORY, resync_after, DRBD_MINOR_NUMBER_DEF) + __u32_field_def(10, DRBD_GENLA_F_MANDATORY, al_extents, DRBD_AL_EXTENTS_DEF) + __u32_field_def(11, DRBD_GENLA_F_MANDATORY, c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF) + __u32_field_def(12, DRBD_GENLA_F_MANDATORY, c_delay_target, DRBD_C_DELAY_TARGET_DEF) + __u32_field_def(13, DRBD_GENLA_F_MANDATORY, c_fill_target, DRBD_C_FILL_TARGET_DEF) + __u32_field_def(14, DRBD_GENLA_F_MANDATORY, c_max_rate, DRBD_C_MAX_RATE_DEF) + __u32_field_def(15, DRBD_GENLA_F_MANDATORY, c_min_rate, DRBD_C_MIN_RATE_DEF) + + __flg_field_def(16, DRBD_GENLA_F_MANDATORY, disk_barrier, DRBD_DISK_BARRIER_DEF) + __flg_field_def(17, DRBD_GENLA_F_MANDATORY, disk_flushes, DRBD_DISK_FLUSHES_DEF) + __flg_field_def(18, DRBD_GENLA_F_MANDATORY, disk_drain, DRBD_DISK_DRAIN_DEF) + __flg_field_def(19, DRBD_GENLA_F_MANDATORY, md_flushes, DRBD_MD_FLUSHES_DEF) + __u32_field_def(20, DRBD_GENLA_F_MANDATORY, disk_timeout, DRBD_DISK_TIMEOUT_DEF) + __u32_field_def(21, 0 /* OPTIONAL */, read_balancing, DRBD_READ_BALANCING_DEF) + /* 9: __u32_field_def(22, DRBD_GENLA_F_MANDATORY, unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) */ + __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) +) + +GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts, + __str_field_def(1, DRBD_GENLA_F_MANDATORY, cpu_mask, 32) + __u32_field_def(2, DRBD_GENLA_F_MANDATORY, on_no_data, DRBD_ON_NO_DATA_DEF) +) + +GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf, + __str_field_def(1, DRBD_GENLA_F_MANDATORY | DRBD_F_SENSITIVE, + shared_secret, SHARED_SECRET_MAX) + __str_field_def(2, DRBD_GENLA_F_MANDATORY, cram_hmac_alg, SHARED_SECRET_MAX) + __str_field_def(3, DRBD_GENLA_F_MANDATORY, integrity_alg, SHARED_SECRET_MAX) + __str_field_def(4, DRBD_GENLA_F_MANDATORY, verify_alg, SHARED_SECRET_MAX) + __str_field_def(5, DRBD_GENLA_F_MANDATORY, csums_alg, SHARED_SECRET_MAX) + __u32_field_def(6, DRBD_GENLA_F_MANDATORY, wire_protocol, DRBD_PROTOCOL_DEF) + __u32_field_def(7, DRBD_GENLA_F_MANDATORY, connect_int, DRBD_CONNECT_INT_DEF) + __u32_field_def(8, DRBD_GENLA_F_MANDATORY, timeout, DRBD_TIMEOUT_DEF) + __u32_field_def(9, DRBD_GENLA_F_MANDATORY, ping_int, DRBD_PING_INT_DEF) + __u32_field_def(10, DRBD_GENLA_F_MANDATORY, ping_timeo, DRBD_PING_TIMEO_DEF) + __u32_field_def(11, DRBD_GENLA_F_MANDATORY, sndbuf_size, DRBD_SNDBUF_SIZE_DEF) + __u32_field_def(12, DRBD_GENLA_F_MANDATORY, rcvbuf_size, DRBD_RCVBUF_SIZE_DEF) + __u32_field_def(13, DRBD_GENLA_F_MANDATORY, ko_count, DRBD_KO_COUNT_DEF) + __u32_field_def(14, DRBD_GENLA_F_MANDATORY, max_buffers, DRBD_MAX_BUFFERS_DEF) + __u32_field_def(15, DRBD_GENLA_F_MANDATORY, max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF) + __u32_field_def(16, DRBD_GENLA_F_MANDATORY, unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) + __u32_field_def(17, DRBD_GENLA_F_MANDATORY, after_sb_0p, DRBD_AFTER_SB_0P_DEF) + __u32_field_def(18, DRBD_GENLA_F_MANDATORY, after_sb_1p, DRBD_AFTER_SB_1P_DEF) + __u32_field_def(19, DRBD_GENLA_F_MANDATORY, after_sb_2p, DRBD_AFTER_SB_2P_DEF) + __u32_field_def(20, DRBD_GENLA_F_MANDATORY, rr_conflict, DRBD_RR_CONFLICT_DEF) + __u32_field_def(21, DRBD_GENLA_F_MANDATORY, on_congestion, DRBD_ON_CONGESTION_DEF) + __u32_field_def(22, DRBD_GENLA_F_MANDATORY, cong_fill, DRBD_CONG_FILL_DEF) + __u32_field_def(23, DRBD_GENLA_F_MANDATORY, cong_extents, DRBD_CONG_EXTENTS_DEF) + __flg_field_def(24, DRBD_GENLA_F_MANDATORY, two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF) + __flg_field(25, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT, discard_my_data) + __flg_field_def(26, DRBD_GENLA_F_MANDATORY, tcp_cork, DRBD_TCP_CORK_DEF) + __flg_field_def(27, DRBD_GENLA_F_MANDATORY, always_asbp, DRBD_ALWAYS_ASBP_DEF) + __flg_field(28, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT, tentative) + __flg_field_def(29, DRBD_GENLA_F_MANDATORY, use_rle, DRBD_USE_RLE_DEF) + /* 9: __u32_field_def(30, DRBD_GENLA_F_MANDATORY, fencing_policy, DRBD_FENCING_DEF) */ +) + +GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms, + __flg_field(1, DRBD_GENLA_F_MANDATORY, assume_uptodate) +) + +GENL_struct(DRBD_NLA_RESIZE_PARMS, 7, resize_parms, + __u64_field(1, DRBD_GENLA_F_MANDATORY, resize_size) + __flg_field(2, DRBD_GENLA_F_MANDATORY, resize_force) + __flg_field(3, DRBD_GENLA_F_MANDATORY, no_resync) +) + +GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info, + /* the reason of the broadcast, + * if this is an event triggered broadcast. */ + __u32_field(1, DRBD_GENLA_F_MANDATORY, sib_reason) + __u32_field(2, DRBD_F_REQUIRED, current_state) + __u64_field(3, DRBD_GENLA_F_MANDATORY, capacity) + __u64_field(4, DRBD_GENLA_F_MANDATORY, ed_uuid) + + /* These are for broadcast from after state change work. + * prev_state and new_state are from the moment the state change took + * place, new_state is not neccessarily the same as current_state, + * there may have been more state changes since. Which will be + * broadcasted soon, in their respective after state change work. */ + __u32_field(5, DRBD_GENLA_F_MANDATORY, prev_state) + __u32_field(6, DRBD_GENLA_F_MANDATORY, new_state) + + /* if we have a local disk: */ + __bin_field(7, DRBD_GENLA_F_MANDATORY, uuids, (UI_SIZE*sizeof(__u64))) + __u32_field(8, DRBD_GENLA_F_MANDATORY, disk_flags) + __u64_field(9, DRBD_GENLA_F_MANDATORY, bits_total) + __u64_field(10, DRBD_GENLA_F_MANDATORY, bits_oos) + /* and in case resync or online verify is active */ + __u64_field(11, DRBD_GENLA_F_MANDATORY, bits_rs_total) + __u64_field(12, DRBD_GENLA_F_MANDATORY, bits_rs_failed) + + /* for pre and post notifications of helper execution */ + __str_field(13, DRBD_GENLA_F_MANDATORY, helper, 32) + __u32_field(14, DRBD_GENLA_F_MANDATORY, helper_exit_code) + + __u64_field(15, 0, send_cnt) + __u64_field(16, 0, recv_cnt) + __u64_field(17, 0, read_cnt) + __u64_field(18, 0, writ_cnt) + __u64_field(19, 0, al_writ_cnt) + __u64_field(20, 0, bm_writ_cnt) + __u32_field(21, 0, ap_bio_cnt) + __u32_field(22, 0, ap_pending_cnt) + __u32_field(23, 0, rs_pending_cnt) +) + +GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms, + __u64_field(1, DRBD_GENLA_F_MANDATORY, ov_start_sector) + __u64_field(2, DRBD_GENLA_F_MANDATORY, ov_stop_sector) +) + +GENL_struct(DRBD_NLA_NEW_C_UUID_PARMS, 10, new_c_uuid_parms, + __flg_field(1, DRBD_GENLA_F_MANDATORY, clear_bm) +) + +GENL_struct(DRBD_NLA_TIMEOUT_PARMS, 11, timeout_parms, + __u32_field(1, DRBD_F_REQUIRED, timeout_type) +) + +GENL_struct(DRBD_NLA_DISCONNECT_PARMS, 12, disconnect_parms, + __flg_field(1, DRBD_GENLA_F_MANDATORY, force_disconnect) +) + +GENL_struct(DRBD_NLA_DETACH_PARMS, 13, detach_parms, + __flg_field(1, DRBD_GENLA_F_MANDATORY, force_detach) +) + +/* + * Notifications and commands (genlmsghdr->cmd) + */ +GENL_mc_group(events) + + /* kernel -> userspace announcement of changes */ +GENL_notification( + DRBD_EVENT, 1, events, + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_STATE_INFO, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_GENLA_F_MANDATORY) + GENL_tla_expected(DRBD_NLA_DISK_CONF, DRBD_GENLA_F_MANDATORY) + GENL_tla_expected(DRBD_NLA_SYNCER_CONF, DRBD_GENLA_F_MANDATORY) +) + + /* query kernel for specific or all info */ +GENL_op( + DRBD_ADM_GET_STATUS, 2, + GENL_op_init( + .doit = drbd_adm_get_status, + .dumpit = drbd_adm_get_status_all, + /* anyone may ask for the status, + * it is broadcasted anyways */ + ), + /* To select the object .doit. + * Or a subset of objects in .dumpit. */ + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY) +) + + /* add DRBD minor devices as volumes to resources */ +GENL_op(DRBD_ADM_NEW_MINOR, 5, GENL_doit(drbd_adm_add_minor), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_delete_minor), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) + + /* add or delete resources */ +GENL_op(DRBD_ADM_NEW_RESOURCE, 7, GENL_doit(drbd_adm_new_resource), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_DEL_RESOURCE, 8, GENL_doit(drbd_adm_del_resource), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) + +GENL_op(DRBD_ADM_RESOURCE_OPTS, 9, + GENL_doit(drbd_adm_resource_opts), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_RESOURCE_OPTS, DRBD_GENLA_F_MANDATORY) +) + +GENL_op( + DRBD_ADM_CONNECT, 10, + GENL_doit(drbd_adm_connect), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED) +) + +GENL_op( + DRBD_ADM_CHG_NET_OPTS, 29, + GENL_doit(drbd_adm_net_opts), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED) +) + +GENL_op(DRBD_ADM_DISCONNECT, 11, GENL_doit(drbd_adm_disconnect), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) + +GENL_op(DRBD_ADM_ATTACH, 12, + GENL_doit(drbd_adm_attach), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_DISK_CONF, DRBD_F_REQUIRED) +) + +GENL_op(DRBD_ADM_CHG_DISK_OPTS, 28, + GENL_doit(drbd_adm_disk_opts), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_DISK_OPTS, DRBD_F_REQUIRED) +) + +GENL_op( + DRBD_ADM_RESIZE, 13, + GENL_doit(drbd_adm_resize), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_RESIZE_PARMS, DRBD_GENLA_F_MANDATORY) +) + +GENL_op( + DRBD_ADM_PRIMARY, 14, + GENL_doit(drbd_adm_set_role), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, DRBD_F_REQUIRED) +) + +GENL_op( + DRBD_ADM_SECONDARY, 15, + GENL_doit(drbd_adm_set_role), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, DRBD_F_REQUIRED) +) + +GENL_op( + DRBD_ADM_NEW_C_UUID, 16, + GENL_doit(drbd_adm_new_c_uuid), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_NEW_C_UUID_PARMS, DRBD_GENLA_F_MANDATORY) +) + +GENL_op( + DRBD_ADM_START_OV, 17, + GENL_doit(drbd_adm_start_ov), + GENL_tla_expected(DRBD_NLA_START_OV_PARMS, DRBD_GENLA_F_MANDATORY) +) + +GENL_op(DRBD_ADM_DETACH, 18, GENL_doit(drbd_adm_detach), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED) + GENL_tla_expected(DRBD_NLA_DETACH_PARMS, DRBD_GENLA_F_MANDATORY)) + +GENL_op(DRBD_ADM_INVALIDATE, 19, GENL_doit(drbd_adm_invalidate), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_INVAL_PEER, 20, GENL_doit(drbd_adm_invalidate_peer), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_PAUSE_SYNC, 21, GENL_doit(drbd_adm_pause_sync), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_RESUME_SYNC, 22, GENL_doit(drbd_adm_resume_sync), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_SUSPEND_IO, 23, GENL_doit(drbd_adm_suspend_io), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_RESUME_IO, 24, GENL_doit(drbd_adm_resume_io), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_OUTDATE, 25, GENL_doit(drbd_adm_outdate), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) +GENL_op(DRBD_ADM_DOWN, 27, GENL_doit(drbd_adm_down), + GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)) diff --git a/include/linux/drbd_genl_api.h b/include/linux/drbd_genl_api.h new file mode 100644 index 0000000..9ef50d5 --- /dev/null +++ b/include/linux/drbd_genl_api.h @@ -0,0 +1,55 @@ +#ifndef DRBD_GENL_STRUCT_H +#define DRBD_GENL_STRUCT_H + +/** + * struct drbd_genlmsghdr - DRBD specific header used in NETLINK_GENERIC requests + * @minor: + * For admin requests (user -> kernel): which minor device to operate on. + * For (unicast) replies or informational (broadcast) messages + * (kernel -> user): which minor device the information is about. + * If we do not operate on minors, but on connections or resources, + * the minor value shall be (~0), and the attribute DRBD_NLA_CFG_CONTEXT + * is used instead. + * @flags: possible operation modifiers (relevant only for user->kernel): + * DRBD_GENL_F_SET_DEFAULTS + * @volume: + * When creating a new minor (adding it to a resource), the resource needs + * to know which volume number within the resource this is supposed to be. + * The volume number corresponds to the same volume number on the remote side, + * whereas the minor number on the remote side may be different + * (union with flags). + * @ret_code: kernel->userland unicast cfg reply return code (union with flags); + */ +struct drbd_genlmsghdr { + __u32 minor; + union { + __u32 flags; + __s32 ret_code; + }; +}; + +/* To be used in drbd_genlmsghdr.flags */ +enum { + DRBD_GENL_F_SET_DEFAULTS = 1, +}; + +enum drbd_state_info_bcast_reason { + SIB_GET_STATUS_REPLY = 1, + SIB_STATE_CHANGE = 2, + SIB_HELPER_PRE = 3, + SIB_HELPER_POST = 4, + SIB_SYNC_PROGRESS = 5, +}; + +/* hack around predefined gcc/cpp "linux=1", + * we cannot possibly include <1/drbd_genl.h> */ +#undef linux + +#include <linux/drbd.h> +#define GENL_MAGIC_VERSION API_VERSION +#define GENL_MAGIC_FAMILY drbd +#define GENL_MAGIC_FAMILY_HDRSZ sizeof(struct drbd_genlmsghdr) +#define GENL_MAGIC_INCLUDE_FILE <linux/drbd_genl.h> +#include <linux/genl_magic_struct.h> + +#endif diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index fb670bf..1fa19c5 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -16,29 +16,37 @@ #define DEBUG_RANGE_CHECK 0 #define DRBD_MINOR_COUNT_MIN 1 -#define DRBD_MINOR_COUNT_MAX 256 +#define DRBD_MINOR_COUNT_MAX 255 #define DRBD_MINOR_COUNT_DEF 32 +#define DRBD_MINOR_COUNT_SCALE '1' + +#define DRBD_VOLUME_MAX 65535 #define DRBD_DIALOG_REFRESH_MIN 0 #define DRBD_DIALOG_REFRESH_MAX 600 +#define DRBD_DIALOG_REFRESH_SCALE '1' /* valid port number */ #define DRBD_PORT_MIN 1 #define DRBD_PORT_MAX 0xffff +#define DRBD_PORT_SCALE '1' /* startup { */ /* if you want more than 3.4 days, disable */ #define DRBD_WFC_TIMEOUT_MIN 0 #define DRBD_WFC_TIMEOUT_MAX 300000 #define DRBD_WFC_TIMEOUT_DEF 0 +#define DRBD_WFC_TIMEOUT_SCALE '1' #define DRBD_DEGR_WFC_TIMEOUT_MIN 0 #define DRBD_DEGR_WFC_TIMEOUT_MAX 300000 #define DRBD_DEGR_WFC_TIMEOUT_DEF 0 +#define DRBD_DEGR_WFC_TIMEOUT_SCALE '1' #define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0 #define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000 #define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0 +#define DRBD_OUTDATED_WFC_TIMEOUT_SCALE '1' /* }*/ /* net { */ @@ -47,75 +55,91 @@ #define DRBD_TIMEOUT_MIN 1 #define DRBD_TIMEOUT_MAX 600 #define DRBD_TIMEOUT_DEF 60 /* 6 seconds */ +#define DRBD_TIMEOUT_SCALE '1' /* If backing disk takes longer than disk_timeout, mark the disk as failed */ #define DRBD_DISK_TIMEOUT_MIN 0 /* 0 = disabled */ #define DRBD_DISK_TIMEOUT_MAX 6000 /* 10 Minutes */ #define DRBD_DISK_TIMEOUT_DEF 0 /* disabled */ +#define DRBD_DISK_TIMEOUT_SCALE '1' /* active connection retries when C_WF_CONNECTION */ #define DRBD_CONNECT_INT_MIN 1 #define DRBD_CONNECT_INT_MAX 120 #define DRBD_CONNECT_INT_DEF 10 /* seconds */ +#define DRBD_CONNECT_INT_SCALE '1' /* keep-alive probes when idle */ #define DRBD_PING_INT_MIN 1 #define DRBD_PING_INT_MAX 120 #define DRBD_PING_INT_DEF 10 +#define DRBD_PING_INT_SCALE '1' /* timeout for the ping packets.*/ #define DRBD_PING_TIMEO_MIN 1 #define DRBD_PING_TIMEO_MAX 300 #define DRBD_PING_TIMEO_DEF 5 +#define DRBD_PING_TIMEO_SCALE '1' /* max number of write requests between write barriers */ #define DRBD_MAX_EPOCH_SIZE_MIN 1 #define DRBD_MAX_EPOCH_SIZE_MAX 20000 #define DRBD_MAX_EPOCH_SIZE_DEF 2048 +#define DRBD_MAX_EPOCH_SIZE_SCALE '1' /* I don't think that a tcp send buffer of more than 10M is useful */ #define DRBD_SNDBUF_SIZE_MIN 0 #define DRBD_SNDBUF_SIZE_MAX (10<<20) #define DRBD_SNDBUF_SIZE_DEF 0 +#define DRBD_SNDBUF_SIZE_SCALE '1' #define DRBD_RCVBUF_SIZE_MIN 0 #define DRBD_RCVBUF_SIZE_MAX (10<<20) #define DRBD_RCVBUF_SIZE_DEF 0 +#define DRBD_RCVBUF_SIZE_SCALE '1' /* @4k PageSize -> 128kB - 512MB */ #define DRBD_MAX_BUFFERS_MIN 32 #define DRBD_MAX_BUFFERS_MAX 131072 #define DRBD_MAX_BUFFERS_DEF 2048 +#define DRBD_MAX_BUFFERS_SCALE '1' /* @4k PageSize -> 4kB - 512MB */ #define DRBD_UNPLUG_WATERMARK_MIN 1 #define DRBD_UNPLUG_WATERMARK_MAX 131072 #define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16) +#define DRBD_UNPLUG_WATERMARK_SCALE '1' /* 0 is disabled. * 200 should be more than enough even for very short timeouts */ #define DRBD_KO_COUNT_MIN 0 #define DRBD_KO_COUNT_MAX 200 -#define DRBD_KO_COUNT_DEF 0 +#define DRBD_KO_COUNT_DEF 7 +#define DRBD_KO_COUNT_SCALE '1' /* } */ /* syncer { */ /* FIXME allow rate to be zero? */ -#define DRBD_RATE_MIN 1 +#define DRBD_RESYNC_RATE_MIN 1 /* channel bonding 10 GbE, or other hardware */ -#define DRBD_RATE_MAX (4 << 20) -#define DRBD_RATE_DEF 250 /* kb/second */ +#define DRBD_RESYNC_RATE_MAX (4 << 20) +#define DRBD_RESYNC_RATE_DEF 250 +#define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ /* less than 7 would hit performance unnecessarily. - * 3833 is the largest prime that still does fit - * into 64 sectors of activity log */ + * 919 slots context information per transaction, + * 32k activity log, 4k transaction size, + * one transaction in flight: + * 919 * 7 = 6433 */ #define DRBD_AL_EXTENTS_MIN 7 -#define DRBD_AL_EXTENTS_MAX 3833 -#define DRBD_AL_EXTENTS_DEF 127 +#define DRBD_AL_EXTENTS_MAX 6433 +#define DRBD_AL_EXTENTS_DEF 1237 +#define DRBD_AL_EXTENTS_SCALE '1' -#define DRBD_AFTER_MIN -1 -#define DRBD_AFTER_MAX 255 -#define DRBD_AFTER_DEF -1 +#define DRBD_MINOR_NUMBER_MIN -1 +#define DRBD_MINOR_NUMBER_MAX ((1 << 20) - 1) +#define DRBD_MINOR_NUMBER_DEF -1 +#define DRBD_MINOR_NUMBER_SCALE '1' /* } */ @@ -124,11 +148,12 @@ * the upper limit with 64bit kernel, enough ram and flexible meta data * is 1 PiB, currently. */ /* DRBD_MAX_SECTORS */ -#define DRBD_DISK_SIZE_SECT_MIN 0 -#define DRBD_DISK_SIZE_SECT_MAX (1 * (2LLU << 40)) -#define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */ +#define DRBD_DISK_SIZE_MIN 0 +#define DRBD_DISK_SIZE_MAX (1 * (2LLU << 40)) +#define DRBD_DISK_SIZE_DEF 0 /* = disabled = no user size... */ +#define DRBD_DISK_SIZE_SCALE 's' /* sectors */ -#define DRBD_ON_IO_ERROR_DEF EP_PASS_ON +#define DRBD_ON_IO_ERROR_DEF EP_DETACH #define DRBD_FENCING_DEF FP_DONT_CARE #define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT #define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT @@ -136,38 +161,59 @@ #define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT #define DRBD_ON_NO_DATA_DEF OND_IO_ERROR #define DRBD_ON_CONGESTION_DEF OC_BLOCK +#define DRBD_READ_BALANCING_DEF RB_PREFER_LOCAL #define DRBD_MAX_BIO_BVECS_MIN 0 #define DRBD_MAX_BIO_BVECS_MAX 128 #define DRBD_MAX_BIO_BVECS_DEF 0 +#define DRBD_MAX_BIO_BVECS_SCALE '1' #define DRBD_C_PLAN_AHEAD_MIN 0 #define DRBD_C_PLAN_AHEAD_MAX 300 -#define DRBD_C_PLAN_AHEAD_DEF 0 /* RS rate controller disabled by default */ +#define DRBD_C_PLAN_AHEAD_DEF 20 +#define DRBD_C_PLAN_AHEAD_SCALE '1' #define DRBD_C_DELAY_TARGET_MIN 1 #define DRBD_C_DELAY_TARGET_MAX 100 #define DRBD_C_DELAY_TARGET_DEF 10 +#define DRBD_C_DELAY_TARGET_SCALE '1' #define DRBD_C_FILL_TARGET_MIN 0 #define DRBD_C_FILL_TARGET_MAX (1<<20) /* 500MByte in sec */ -#define DRBD_C_FILL_TARGET_DEF 0 /* By default disabled -> controlled by delay_target */ +#define DRBD_C_FILL_TARGET_DEF 100 /* Try to place 50KiB in socket send buffer during resync */ +#define DRBD_C_FILL_TARGET_SCALE 's' /* sectors */ -#define DRBD_C_MAX_RATE_MIN 250 /* kByte/sec */ +#define DRBD_C_MAX_RATE_MIN 250 #define DRBD_C_MAX_RATE_MAX (4 << 20) #define DRBD_C_MAX_RATE_DEF 102400 +#define DRBD_C_MAX_RATE_SCALE 'k' /* kilobytes */ -#define DRBD_C_MIN_RATE_MIN 0 /* kByte/sec */ +#define DRBD_C_MIN_RATE_MIN 0 #define DRBD_C_MIN_RATE_MAX (4 << 20) -#define DRBD_C_MIN_RATE_DEF 4096 +#define DRBD_C_MIN_RATE_DEF 250 +#define DRBD_C_MIN_RATE_SCALE 'k' /* kilobytes */ #define DRBD_CONG_FILL_MIN 0 #define DRBD_CONG_FILL_MAX (10<<21) /* 10GByte in sectors */ #define DRBD_CONG_FILL_DEF 0 +#define DRBD_CONG_FILL_SCALE 's' /* sectors */ #define DRBD_CONG_EXTENTS_MIN DRBD_AL_EXTENTS_MIN #define DRBD_CONG_EXTENTS_MAX DRBD_AL_EXTENTS_MAX #define DRBD_CONG_EXTENTS_DEF DRBD_AL_EXTENTS_DEF +#define DRBD_CONG_EXTENTS_SCALE DRBD_AL_EXTENTS_SCALE + +#define DRBD_PROTOCOL_DEF DRBD_PROT_C + +#define DRBD_DISK_BARRIER_DEF 0 +#define DRBD_DISK_FLUSHES_DEF 1 +#define DRBD_DISK_DRAIN_DEF 1 +#define DRBD_MD_FLUSHES_DEF 1 +#define DRBD_TCP_CORK_DEF 1 +#define DRBD_AL_UPDATES_DEF 1 + +#define DRBD_ALLOW_TWO_PRIMARIES_DEF 0 +#define DRBD_ALWAYS_ASBP_DEF 0 +#define DRBD_USE_RLE_DEF 1 -#undef RANGE #endif diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h deleted file mode 100644 index a8706f0..0000000 --- a/include/linux/drbd_nl.h +++ /dev/null @@ -1,163 +0,0 @@ -/* - PAKET( name, - TYPE ( pn, pr, member ) - ... - ) - - You may never reissue one of the pn arguments -*/ - -#if !defined(NL_PACKET) || !defined(NL_STRING) || !defined(NL_INTEGER) || !defined(NL_BIT) || !defined(NL_INT64) -#error "The macros NL_PACKET, NL_STRING, NL_INTEGER, NL_INT64 and NL_BIT needs to be defined" -#endif - -NL_PACKET(primary, 1, - NL_BIT( 1, T_MAY_IGNORE, primary_force) -) - -NL_PACKET(secondary, 2, ) - -NL_PACKET(disk_conf, 3, - NL_INT64( 2, T_MAY_IGNORE, disk_size) - NL_STRING( 3, T_MANDATORY, backing_dev, 128) - NL_STRING( 4, T_MANDATORY, meta_dev, 128) - NL_INTEGER( 5, T_MANDATORY, meta_dev_idx) - NL_INTEGER( 6, T_MAY_IGNORE, on_io_error) - NL_INTEGER( 7, T_MAY_IGNORE, fencing) - NL_BIT( 37, T_MAY_IGNORE, use_bmbv) - NL_BIT( 53, T_MAY_IGNORE, no_disk_flush) - NL_BIT( 54, T_MAY_IGNORE, no_md_flush) - /* 55 max_bio_size was available in 8.2.6rc2 */ - NL_INTEGER( 56, T_MAY_IGNORE, max_bio_bvecs) - NL_BIT( 57, T_MAY_IGNORE, no_disk_barrier) - NL_BIT( 58, T_MAY_IGNORE, no_disk_drain) - NL_INTEGER( 89, T_MAY_IGNORE, disk_timeout) -) - -NL_PACKET(detach, 4, - NL_BIT( 88, T_MANDATORY, detach_force) -) - -NL_PACKET(net_conf, 5, - NL_STRING( 8, T_MANDATORY, my_addr, 128) - NL_STRING( 9, T_MANDATORY, peer_addr, 128) - NL_STRING( 10, T_MAY_IGNORE, shared_secret, SHARED_SECRET_MAX) - NL_STRING( 11, T_MAY_IGNORE, cram_hmac_alg, SHARED_SECRET_MAX) - NL_STRING( 44, T_MAY_IGNORE, integrity_alg, SHARED_SECRET_MAX) - NL_INTEGER( 14, T_MAY_IGNORE, timeout) - NL_INTEGER( 15, T_MANDATORY, wire_protocol) - NL_INTEGER( 16, T_MAY_IGNORE, try_connect_int) - NL_INTEGER( 17, T_MAY_IGNORE, ping_int) - NL_INTEGER( 18, T_MAY_IGNORE, max_epoch_size) - NL_INTEGER( 19, T_MAY_IGNORE, max_buffers) - NL_INTEGER( 20, T_MAY_IGNORE, unplug_watermark) - NL_INTEGER( 21, T_MAY_IGNORE, sndbuf_size) - NL_INTEGER( 22, T_MAY_IGNORE, ko_count) - NL_INTEGER( 24, T_MAY_IGNORE, after_sb_0p) - NL_INTEGER( 25, T_MAY_IGNORE, after_sb_1p) - NL_INTEGER( 26, T_MAY_IGNORE, after_sb_2p) - NL_INTEGER( 39, T_MAY_IGNORE, rr_conflict) - NL_INTEGER( 40, T_MAY_IGNORE, ping_timeo) - NL_INTEGER( 67, T_MAY_IGNORE, rcvbuf_size) - NL_INTEGER( 81, T_MAY_IGNORE, on_congestion) - NL_INTEGER( 82, T_MAY_IGNORE, cong_fill) - NL_INTEGER( 83, T_MAY_IGNORE, cong_extents) - /* 59 addr_family was available in GIT, never released */ - NL_BIT( 60, T_MANDATORY, mind_af) - NL_BIT( 27, T_MAY_IGNORE, want_lose) - NL_BIT( 28, T_MAY_IGNORE, two_primaries) - NL_BIT( 41, T_MAY_IGNORE, always_asbp) - NL_BIT( 61, T_MAY_IGNORE, no_cork) - NL_BIT( 62, T_MANDATORY, auto_sndbuf_size) - NL_BIT( 70, T_MANDATORY, dry_run) -) - -NL_PACKET(disconnect, 6, - NL_BIT( 84, T_MAY_IGNORE, force) -) - -NL_PACKET(resize, 7, - NL_INT64( 29, T_MAY_IGNORE, resize_size) - NL_BIT( 68, T_MAY_IGNORE, resize_force) - NL_BIT( 69, T_MANDATORY, no_resync) -) - -NL_PACKET(syncer_conf, 8, - NL_INTEGER( 30, T_MAY_IGNORE, rate) - NL_INTEGER( 31, T_MAY_IGNORE, after) - NL_INTEGER( 32, T_MAY_IGNORE, al_extents) -/* NL_INTEGER( 71, T_MAY_IGNORE, dp_volume) - * NL_INTEGER( 72, T_MAY_IGNORE, dp_interval) - * NL_INTEGER( 73, T_MAY_IGNORE, throttle_th) - * NL_INTEGER( 74, T_MAY_IGNORE, hold_off_th) - * feature will be reimplemented differently with 8.3.9 */ - NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX) - NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32) - NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX) - NL_BIT( 65, T_MAY_IGNORE, use_rle) - NL_INTEGER( 75, T_MAY_IGNORE, on_no_data) - NL_INTEGER( 76, T_MAY_IGNORE, c_plan_ahead) - NL_INTEGER( 77, T_MAY_IGNORE, c_delay_target) - NL_INTEGER( 78, T_MAY_IGNORE, c_fill_target) - NL_INTEGER( 79, T_MAY_IGNORE, c_max_rate) - NL_INTEGER( 80, T_MAY_IGNORE, c_min_rate) -) - -NL_PACKET(invalidate, 9, ) -NL_PACKET(invalidate_peer, 10, ) -NL_PACKET(pause_sync, 11, ) -NL_PACKET(resume_sync, 12, ) -NL_PACKET(suspend_io, 13, ) -NL_PACKET(resume_io, 14, ) -NL_PACKET(outdate, 15, ) -NL_PACKET(get_config, 16, ) -NL_PACKET(get_state, 17, - NL_INTEGER( 33, T_MAY_IGNORE, state_i) -) - -NL_PACKET(get_uuids, 18, - NL_STRING( 34, T_MAY_IGNORE, uuids, (UI_SIZE*sizeof(__u64))) - NL_INTEGER( 35, T_MAY_IGNORE, uuids_flags) -) - -NL_PACKET(get_timeout_flag, 19, - NL_BIT( 36, T_MAY_IGNORE, use_degraded) -) - -NL_PACKET(call_helper, 20, - NL_STRING( 38, T_MAY_IGNORE, helper, 32) -) - -/* Tag nr 42 already allocated in drbd-8.1 development. */ - -NL_PACKET(sync_progress, 23, - NL_INTEGER( 43, T_MAY_IGNORE, sync_progress) -) - -NL_PACKET(dump_ee, 24, - NL_STRING( 45, T_MAY_IGNORE, dump_ee_reason, 32) - NL_STRING( 46, T_MAY_IGNORE, seen_digest, SHARED_SECRET_MAX) - NL_STRING( 47, T_MAY_IGNORE, calc_digest, SHARED_SECRET_MAX) - NL_INT64( 48, T_MAY_IGNORE, ee_sector) - NL_INT64( 49, T_MAY_IGNORE, ee_block_id) - NL_STRING( 50, T_MAY_IGNORE, ee_data, 32 << 10) -) - -NL_PACKET(start_ov, 25, - NL_INT64( 66, T_MAY_IGNORE, start_sector) -) - -NL_PACKET(new_c_uuid, 26, - NL_BIT( 63, T_MANDATORY, clear_bm) -) - -#ifdef NL_RESPONSE -NL_RESPONSE(return_code_only, 27) -#endif - -#undef NL_PACKET -#undef NL_INTEGER -#undef NL_INT64 -#undef NL_BIT -#undef NL_STRING -#undef NL_RESPONSE diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h deleted file mode 100644 index 82de1f9..0000000 --- a/include/linux/drbd_tag_magic.h +++ /dev/null @@ -1,84 +0,0 @@ -#ifndef DRBD_TAG_MAGIC_H -#define DRBD_TAG_MAGIC_H - -#define TT_END 0 -#define TT_REMOVED 0xE000 - -/* declare packet_type enums */ -enum packet_types { -#define NL_PACKET(name, number, fields) P_ ## name = number, -#define NL_RESPONSE(name, number) P_ ## name = number, -#define NL_INTEGER(pn, pr, member) -#define NL_INT64(pn, pr, member) -#define NL_BIT(pn, pr, member) -#define NL_STRING(pn, pr, member, len) -#include <linux/drbd_nl.h> - P_nl_after_last_packet, -}; - -/* These struct are used to deduce the size of the tag lists: */ -#define NL_PACKET(name, number, fields) \ - struct name ## _tag_len_struct { fields }; -#define NL_INTEGER(pn, pr, member) \ - int member; int tag_and_len ## member; -#define NL_INT64(pn, pr, member) \ - __u64 member; int tag_and_len ## member; -#define NL_BIT(pn, pr, member) \ - unsigned char member:1; int tag_and_len ## member; -#define NL_STRING(pn, pr, member, len) \ - unsigned char member[len]; int member ## _len; \ - int tag_and_len ## member; -#include <linux/drbd_nl.h> - -/* declare tag-list-sizes */ -static const int tag_list_sizes[] = { -#define NL_PACKET(name, number, fields) 2 fields , -#define NL_INTEGER(pn, pr, member) + 4 + 4 -#define NL_INT64(pn, pr, member) + 4 + 8 -#define NL_BIT(pn, pr, member) + 4 + 1 -#define NL_STRING(pn, pr, member, len) + 4 + (len) -#include <linux/drbd_nl.h> -}; - -/* The two highest bits are used for the tag type */ -#define TT_MASK 0xC000 -#define TT_INTEGER 0x0000 -#define TT_INT64 0x4000 -#define TT_BIT 0x8000 -#define TT_STRING 0xC000 -/* The next bit indicates if processing of the tag is mandatory */ -#define T_MANDATORY 0x2000 -#define T_MAY_IGNORE 0x0000 -#define TN_MASK 0x1fff -/* The remaining 13 bits are used to enumerate the tags */ - -#define tag_type(T) ((T) & TT_MASK) -#define tag_number(T) ((T) & TN_MASK) - -/* declare tag enums */ -#define NL_PACKET(name, number, fields) fields -enum drbd_tags { -#define NL_INTEGER(pn, pr, member) T_ ## member = pn | TT_INTEGER | pr , -#define NL_INT64(pn, pr, member) T_ ## member = pn | TT_INT64 | pr , -#define NL_BIT(pn, pr, member) T_ ## member = pn | TT_BIT | pr , -#define NL_STRING(pn, pr, member, len) T_ ## member = pn | TT_STRING | pr , -#include <linux/drbd_nl.h> -}; - -struct tag { - const char *name; - int type_n_flags; - int max_len; -}; - -/* declare tag names */ -#define NL_PACKET(name, number, fields) fields -static const struct tag tag_descriptions[] = { -#define NL_INTEGER(pn, pr, member) [ pn ] = { #member, TT_INTEGER | pr, sizeof(int) }, -#define NL_INT64(pn, pr, member) [ pn ] = { #member, TT_INT64 | pr, sizeof(__u64) }, -#define NL_BIT(pn, pr, member) [ pn ] = { #member, TT_BIT | pr, sizeof(int) }, -#define NL_STRING(pn, pr, member, len) [ pn ] = { #member, TT_STRING | pr, (len) }, -#include <linux/drbd_nl.h> -}; - -#endif diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 12291a7..c7e6b63 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -177,6 +177,8 @@ struct export_operations { int (*commit_metadata)(struct inode *inode); }; +extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, + int *max_len, struct inode *parent); extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len, int connectable); extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, diff --git a/include/linux/fs.h b/include/linux/fs.h index 408fb1e..a823d4b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -44,6 +44,7 @@ struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; +struct seq_file; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -1543,6 +1544,7 @@ struct file_operations { int (*setlease)(struct file *, long, struct file_lock **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); + int (*show_fdinfo)(struct seq_file *m, struct file *f); }; struct inode_operations { @@ -1578,8 +1580,6 @@ struct inode_operations { umode_t create_mode, int *opened); } ____cacheline_aligned; -struct seq_file; - ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, @@ -1810,6 +1810,8 @@ struct file_system_type { #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 +#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ +#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ #define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, @@ -2286,9 +2288,9 @@ extern ino_t find_inode_number(struct dentry *, struct qstr *); #include <linux/err.h> /* needed for stackable file system support */ -extern loff_t default_llseek(struct file *file, loff_t offset, int origin); +extern loff_t default_llseek(struct file *file, loff_t offset, int whence); -extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); +extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); @@ -2396,11 +2398,11 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern loff_t noop_llseek(struct file *file, loff_t offset, int origin); -extern loff_t no_llseek(struct file *file, loff_t offset, int origin); -extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); +extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); +extern loff_t no_llseek(struct file *file, loff_t offset, int whence); +extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, - int origin, loff_t maxsize, loff_t eof); + int whence, loff_t maxsize, loff_t eof); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a52f2f4..92691d8 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -394,7 +394,7 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int origin); +loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init @@ -559,7 +559,7 @@ static inline ssize_t ftrace_filter_write(struct file *file, const char __user * size_t cnt, loff_t *ppos) { return -ENODEV; } static inline ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { return -ENODEV; } -static inline loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int origin) +static inline loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence) { return -ENODEV; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 4f440b3..79b8bba 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -88,10 +88,14 @@ struct disk_stats { }; #define PARTITION_META_INFO_VOLNAMELTH 64 -#define PARTITION_META_INFO_UUIDLTH 16 +/* + * Enough for the string representation of any kind of UUID plus NULL. + * EFI UUID is 36 characters. MSDOS UUID is 11 characters. + */ +#define PARTITION_META_INFO_UUIDLTH 37 struct partition_meta_info { - u8 uuid[PARTITION_META_INFO_UUIDLTH]; /* always big endian */ + char uuid[PARTITION_META_INFO_UUIDLTH]; u8 volname[PARTITION_META_INFO_VOLNAMELTH]; }; diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h new file mode 100644 index 0000000..023bc34 --- /dev/null +++ b/include/linux/genl_magic_func.h @@ -0,0 +1,422 @@ +#ifndef GENL_MAGIC_FUNC_H +#define GENL_MAGIC_FUNC_H + +#include <linux/genl_magic_struct.h> + +/* + * Magic: declare tla policy {{{1 + * Magic: declare nested policies + * {{{2 + */ +#undef GENL_mc_group +#define GENL_mc_group(group) + +#undef GENL_notification +#define GENL_notification(op_name, op_num, mcast_group, tla_list) + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, tla_list) + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ + [tag_name] = { .type = NLA_NESTED }, + +static struct nla_policy CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy)[] = { +#include GENL_MAGIC_INCLUDE_FILE +}; + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +static struct nla_policy s_name ## _nl_policy[] __read_mostly = \ +{ s_fields }; + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, _type, __get, \ + __put, __is_signed) \ + [attr_nr] = { .type = nla_type }, + +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, _type, maxlen, \ + __get, __put, __is_signed) \ + [attr_nr] = { .type = nla_type, \ + .len = maxlen - (nla_type == NLA_NUL_STRING) }, + +#include GENL_MAGIC_INCLUDE_FILE + +#ifndef __KERNEL__ +#ifndef pr_info +#define pr_info(args...) fprintf(stderr, args); +#endif +#endif + +#ifdef GENL_MAGIC_DEBUG +static void dprint_field(const char *dir, int nla_type, + const char *name, void *valp) +{ + __u64 val = valp ? *(__u32 *)valp : 1; + switch (nla_type) { + case NLA_U8: val = (__u8)val; + case NLA_U16: val = (__u16)val; + case NLA_U32: val = (__u32)val; + pr_info("%s attr %s: %d 0x%08x\n", dir, + name, (int)val, (unsigned)val); + break; + case NLA_U64: + val = *(__u64*)valp; + pr_info("%s attr %s: %lld 0x%08llx\n", dir, + name, (long long)val, (unsigned long long)val); + break; + case NLA_FLAG: + if (val) + pr_info("%s attr %s: set\n", dir, name); + break; + } +} + +static void dprint_array(const char *dir, int nla_type, + const char *name, const char *val, unsigned len) +{ + switch (nla_type) { + case NLA_NUL_STRING: + if (len && val[len-1] == '\0') + len--; + pr_info("%s attr %s: [len:%u] '%s'\n", dir, name, len, val); + break; + default: + /* we can always show 4 byte, + * thats what nlattr are aligned to. */ + pr_info("%s attr %s: [len:%u] %02x%02x%02x%02x ...\n", + dir, name, len, val[0], val[1], val[2], val[3]); + } +} + +#define DPRINT_TLA(a, op, b) pr_info("%s %s %s\n", a, op, b); + +/* Name is a member field name of the struct s. + * If s is NULL (only parsing, no copy requested in *_from_attrs()), + * nla is supposed to point to the attribute containing the information + * corresponding to that struct member. */ +#define DPRINT_FIELD(dir, nla_type, name, s, nla) \ + do { \ + if (s) \ + dprint_field(dir, nla_type, #name, &s->name); \ + else if (nla) \ + dprint_field(dir, nla_type, #name, \ + (nla_type == NLA_FLAG) ? NULL \ + : nla_data(nla)); \ + } while (0) + +#define DPRINT_ARRAY(dir, nla_type, name, s, nla) \ + do { \ + if (s) \ + dprint_array(dir, nla_type, #name, \ + s->name, s->name ## _len); \ + else if (nla) \ + dprint_array(dir, nla_type, #name, \ + nla_data(nla), nla_len(nla)); \ + } while (0) +#else +#define DPRINT_TLA(a, op, b) do {} while (0) +#define DPRINT_FIELD(dir, nla_type, name, s, nla) do {} while (0) +#define DPRINT_ARRAY(dir, nla_type, name, s, nla) do {} while (0) +#endif + +/* + * Magic: provide conversion functions {{{1 + * populate struct from attribute table: + * {{{2 + */ + +/* processing of generic netlink messages is serialized. + * use one static buffer for parsing of nested attributes */ +static struct nlattr *nested_attr_tb[128]; + +#ifndef BUILD_BUG_ON +/* Force a compilation error if condition is true */ +#define BUILD_BUG_ON(condition) ((void)BUILD_BUG_ON_ZERO(condition)) +/* Force a compilation error if condition is true, but also produce a + result (of value 0 and type size_t), so the expression can be used + e.g. in a structure initializer (or where-ever else comma expressions + aren't permitted). */ +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) +#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) +#endif + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +/* *_from_attrs functions are static, but potentially unused */ \ +static int __ ## s_name ## _from_attrs(struct s_name *s, \ + struct genl_info *info, bool exclude_invariants) \ +{ \ + const int maxtype = ARRAY_SIZE(s_name ## _nl_policy)-1; \ + struct nlattr *tla = info->attrs[tag_number]; \ + struct nlattr **ntb = nested_attr_tb; \ + struct nlattr *nla; \ + int err; \ + BUILD_BUG_ON(ARRAY_SIZE(s_name ## _nl_policy) > ARRAY_SIZE(nested_attr_tb)); \ + if (!tla) \ + return -ENOMSG; \ + DPRINT_TLA(#s_name, "<=-", #tag_name); \ + err = drbd_nla_parse_nested(ntb, maxtype, tla, s_name ## _nl_policy); \ + if (err) \ + return err; \ + \ + s_fields \ + return 0; \ +} __attribute__((unused)) \ +static int s_name ## _from_attrs(struct s_name *s, \ + struct genl_info *info) \ +{ \ + return __ ## s_name ## _from_attrs(s, info, false); \ +} __attribute__((unused)) \ +static int s_name ## _from_attrs_for_change(struct s_name *s, \ + struct genl_info *info) \ +{ \ + return __ ## s_name ## _from_attrs(s, info, true); \ +} __attribute__((unused)) \ + +#define __assign(attr_nr, attr_flag, name, nla_type, type, assignment...) \ + nla = ntb[attr_nr]; \ + if (nla) { \ + if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) { \ + pr_info("<< must not change invariant attr: %s\n", #name); \ + return -EEXIST; \ + } \ + assignment; \ + } else if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) { \ + /* attribute missing from payload, */ \ + /* which was expected */ \ + } else if ((attr_flag) & DRBD_F_REQUIRED) { \ + pr_info("<< missing attr: %s\n", #name); \ + return -ENOMSG; \ + } + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ + __is_signed) \ + __assign(attr_nr, attr_flag, name, nla_type, type, \ + if (s) \ + s->name = __get(nla); \ + DPRINT_FIELD("<<", nla_type, name, s, nla)) + +/* validate_nla() already checked nla_len <= maxlen appropriately. */ +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ + __get, __put, __is_signed) \ + __assign(attr_nr, attr_flag, name, nla_type, type, \ + if (s) \ + s->name ## _len = \ + __get(s->name, nla, maxlen); \ + DPRINT_ARRAY("<<", nla_type, name, s, nla)) + +#include GENL_MAGIC_INCLUDE_FILE + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) + +/* + * Magic: define op number to op name mapping {{{1 + * {{{2 + */ +const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) +{ + switch (cmd) { +#undef GENL_op +#define GENL_op(op_name, op_num, handler, tla_list) \ + case op_num: return #op_name; +#include GENL_MAGIC_INCLUDE_FILE + default: + return "unknown"; + } +} + +#ifdef __KERNEL__ +#include <linux/stringify.h> +/* + * Magic: define genl_ops {{{1 + * {{{2 + */ + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, tla_list) \ +{ \ + handler \ + .cmd = op_name, \ + .policy = CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy), \ +}, + +#define ZZZ_genl_ops CONCAT_(GENL_MAGIC_FAMILY, _genl_ops) +static struct genl_ops ZZZ_genl_ops[] __read_mostly = { +#include GENL_MAGIC_INCLUDE_FILE +}; + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, tla_list) + +/* + * Define the genl_family, multicast groups, {{{1 + * and provide register/unregister functions. + * {{{2 + */ +#define ZZZ_genl_family CONCAT_(GENL_MAGIC_FAMILY, _genl_family) +static struct genl_family ZZZ_genl_family __read_mostly = { + .id = GENL_ID_GENERATE, + .name = __stringify(GENL_MAGIC_FAMILY), + .version = GENL_MAGIC_VERSION, +#ifdef GENL_MAGIC_FAMILY_HDRSZ + .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), +#endif + .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, +}; + +/* + * Magic: define multicast groups + * Magic: define multicast group registration helper + */ +#undef GENL_mc_group +#define GENL_mc_group(group) \ +static struct genl_multicast_group \ +CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group) __read_mostly = { \ + .name = #group, \ +}; \ +static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)( \ + struct sk_buff *skb, gfp_t flags) \ +{ \ + unsigned int group_id = \ + CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id; \ + if (!group_id) \ + return -EINVAL; \ + return genlmsg_multicast(skb, 0, group_id, flags); \ +} + +#include GENL_MAGIC_INCLUDE_FILE + +int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void) +{ + int err = genl_register_family_with_ops(&ZZZ_genl_family, + ZZZ_genl_ops, ARRAY_SIZE(ZZZ_genl_ops)); + if (err) + return err; +#undef GENL_mc_group +#define GENL_mc_group(group) \ + err = genl_register_mc_group(&ZZZ_genl_family, \ + &CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group)); \ + if (err) \ + goto fail; \ + else \ + pr_info("%s: mcg %s: %u\n", #group, \ + __stringify(GENL_MAGIC_FAMILY), \ + CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id); + +#include GENL_MAGIC_INCLUDE_FILE + +#undef GENL_mc_group +#define GENL_mc_group(group) + return 0; +fail: + genl_unregister_family(&ZZZ_genl_family); + return err; +} + +void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void) +{ + genl_unregister_family(&ZZZ_genl_family); +} + +/* + * Magic: provide conversion functions {{{1 + * populate skb from struct. + * {{{2 + */ + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, tla_list) + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +static int s_name ## _to_skb(struct sk_buff *skb, struct s_name *s, \ + const bool exclude_sensitive) \ +{ \ + struct nlattr *tla = nla_nest_start(skb, tag_number); \ + if (!tla) \ + goto nla_put_failure; \ + DPRINT_TLA(#s_name, "-=>", #tag_name); \ + s_fields \ + nla_nest_end(skb, tla); \ + return 0; \ + \ +nla_put_failure: \ + if (tla) \ + nla_nest_cancel(skb, tla); \ + return -EMSGSIZE; \ +} \ +static inline int s_name ## _to_priv_skb(struct sk_buff *skb, \ + struct s_name *s) \ +{ \ + return s_name ## _to_skb(skb, s, 0); \ +} \ +static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb, \ + struct s_name *s) \ +{ \ + return s_name ## _to_skb(skb, s, 1); \ +} + + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ + __is_signed) \ + if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) { \ + DPRINT_FIELD(">>", nla_type, name, s, NULL); \ + if (__put(skb, attr_nr, s->name)) \ + goto nla_put_failure; \ + } + +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ + __get, __put, __is_signed) \ + if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) { \ + DPRINT_ARRAY(">>",nla_type, name, s, NULL); \ + if (__put(skb, attr_nr, min_t(int, maxlen, \ + s->name ## _len + (nla_type == NLA_NUL_STRING)),\ + s->name)) \ + goto nla_put_failure; \ + } + +#include GENL_MAGIC_INCLUDE_FILE + + +/* Functions for initializing structs to default values. */ + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ + __is_signed) +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ + __get, __put, __is_signed) +#undef __u32_field_def +#define __u32_field_def(attr_nr, attr_flag, name, default) \ + x->name = default; +#undef __s32_field_def +#define __s32_field_def(attr_nr, attr_flag, name, default) \ + x->name = default; +#undef __flg_field_def +#define __flg_field_def(attr_nr, attr_flag, name, default) \ + x->name = default; +#undef __str_field_def +#define __str_field_def(attr_nr, attr_flag, name, maxlen) \ + memset(x->name, 0, sizeof(x->name)); \ + x->name ## _len = 0; +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +static void set_ ## s_name ## _defaults(struct s_name *x) __attribute__((unused)); \ +static void set_ ## s_name ## _defaults(struct s_name *x) { \ +s_fields \ +} + +#include GENL_MAGIC_INCLUDE_FILE + +#endif /* __KERNEL__ */ + +/* }}}1 */ +#endif /* GENL_MAGIC_FUNC_H */ +/* vim: set foldmethod=marker foldlevel=1 nofoldenable : */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h new file mode 100644 index 0000000..eecd19b --- /dev/null +++ b/include/linux/genl_magic_struct.h @@ -0,0 +1,277 @@ +#ifndef GENL_MAGIC_STRUCT_H +#define GENL_MAGIC_STRUCT_H + +#ifndef GENL_MAGIC_FAMILY +# error "you need to define GENL_MAGIC_FAMILY before inclusion" +#endif + +#ifndef GENL_MAGIC_VERSION +# error "you need to define GENL_MAGIC_VERSION before inclusion" +#endif + +#ifndef GENL_MAGIC_INCLUDE_FILE +# error "you need to define GENL_MAGIC_INCLUDE_FILE before inclusion" +#endif + +#include <linux/genetlink.h> +#include <linux/types.h> + +#define CONCAT__(a,b) a ## b +#define CONCAT_(a,b) CONCAT__(a,b) + +extern int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void); +extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void); + +/* + * Extension of genl attribute validation policies {{{2 + */ + +/* + * @DRBD_GENLA_F_MANDATORY: By default, netlink ignores attributes it does not + * know about. This flag can be set in nlattr->nla_type to indicate that this + * attribute must not be ignored. + * + * We check and remove this flag in drbd_nla_check_mandatory() before + * validating the attribute types and lengths via nla_parse_nested(). + */ +#define DRBD_GENLA_F_MANDATORY (1 << 14) + +/* + * Flags specific to drbd and not visible at the netlink layer, used in + * <struct>_from_attrs and <struct>_to_skb: + * + * @DRBD_F_REQUIRED: Attribute is required; a request without this attribute is + * invalid. + * + * @DRBD_F_SENSITIVE: Attribute includes sensitive information and must not be + * included in unpriviledged get requests or broadcasts. + * + * @DRBD_F_INVARIANT: Attribute is set when an object is initially created, but + * cannot subsequently be changed. + */ +#define DRBD_F_REQUIRED (1 << 0) +#define DRBD_F_SENSITIVE (1 << 1) +#define DRBD_F_INVARIANT (1 << 2) + +#define __nla_type(x) ((__u16)((x) & NLA_TYPE_MASK & ~DRBD_GENLA_F_MANDATORY)) + +/* }}}1 + * MAGIC + * multi-include macro expansion magic starts here + */ + +/* MAGIC helpers {{{2 */ + +/* possible field types */ +#define __flg_field(attr_nr, attr_flag, name) \ + __field(attr_nr, attr_flag, name, NLA_U8, char, \ + nla_get_u8, nla_put_u8, false) +#define __u8_field(attr_nr, attr_flag, name) \ + __field(attr_nr, attr_flag, name, NLA_U8, unsigned char, \ + nla_get_u8, nla_put_u8, false) +#define __u16_field(attr_nr, attr_flag, name) \ + __field(attr_nr, attr_flag, name, NLA_U16, __u16, \ + nla_get_u16, nla_put_u16, false) +#define __u32_field(attr_nr, attr_flag, name) \ + __field(attr_nr, attr_flag, name, NLA_U32, __u32, \ + nla_get_u32, nla_put_u32, false) +#define __s32_field(attr_nr, attr_flag, name) \ + __field(attr_nr, attr_flag, name, NLA_U32, __s32, \ + nla_get_u32, nla_put_u32, true) +#define __u64_field(attr_nr, attr_flag, name) \ + __field(attr_nr, attr_flag, name, NLA_U64, __u64, \ + nla_get_u64, nla_put_u64, false) +#define __str_field(attr_nr, attr_flag, name, maxlen) \ + __array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \ + nla_strlcpy, nla_put, false) +#define __bin_field(attr_nr, attr_flag, name, maxlen) \ + __array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \ + nla_memcpy, nla_put, false) + +/* fields with default values */ +#define __flg_field_def(attr_nr, attr_flag, name, default) \ + __flg_field(attr_nr, attr_flag, name) +#define __u32_field_def(attr_nr, attr_flag, name, default) \ + __u32_field(attr_nr, attr_flag, name) +#define __s32_field_def(attr_nr, attr_flag, name, default) \ + __s32_field(attr_nr, attr_flag, name) +#define __str_field_def(attr_nr, attr_flag, name, maxlen) \ + __str_field(attr_nr, attr_flag, name, maxlen) + +#define GENL_op_init(args...) args +#define GENL_doit(handler) \ + .doit = handler, \ + .flags = GENL_ADMIN_PERM, +#define GENL_dumpit(handler) \ + .dumpit = handler, \ + .flags = GENL_ADMIN_PERM, + +/* }}}1 + * Magic: define the enum symbols for genl_ops + * Magic: define the enum symbols for top level attributes + * Magic: define the enum symbols for nested attributes + * {{{2 + */ + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) + +#undef GENL_mc_group +#define GENL_mc_group(group) + +#undef GENL_notification +#define GENL_notification(op_name, op_num, mcast_group, tla_list) \ + op_name = op_num, + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, tla_list) \ + op_name = op_num, + +enum { +#include GENL_MAGIC_INCLUDE_FILE +}; + +#undef GENL_notification +#define GENL_notification(op_name, op_num, mcast_group, tla_list) + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, attr_list) + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ + tag_name = tag_number, + +enum { +#include GENL_MAGIC_INCLUDE_FILE +}; + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +enum { \ + s_fields \ +}; + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, \ + __get, __put, __is_signed) \ + T_ ## name = (__u16)(attr_nr | ((attr_flag) & DRBD_GENLA_F_MANDATORY)), + +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, \ + maxlen, __get, __put, __is_signed) \ + T_ ## name = (__u16)(attr_nr | ((attr_flag) & DRBD_GENLA_F_MANDATORY)), + +#include GENL_MAGIC_INCLUDE_FILE + +/* }}}1 + * Magic: compile time assert unique numbers for operations + * Magic: -"- unique numbers for top level attributes + * Magic: -"- unique numbers for nested attributes + * {{{2 + */ + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, attr_list) \ + case op_name: + +#undef GENL_notification +#define GENL_notification(op_name, op_num, mcast_group, tla_list) \ + case op_name: + +static inline void ct_assert_unique_operations(void) +{ + switch (0) { +#include GENL_MAGIC_INCLUDE_FILE + ; + } +} + +#undef GENL_op +#define GENL_op(op_name, op_num, handler, attr_list) + +#undef GENL_notification +#define GENL_notification(op_name, op_num, mcast_group, tla_list) + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ + case tag_number: + +static inline void ct_assert_unique_top_level_attributes(void) +{ + switch (0) { +#include GENL_MAGIC_INCLUDE_FILE + ; + } +} + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +static inline void ct_assert_unique_ ## s_name ## _attributes(void) \ +{ \ + switch (0) { \ + s_fields \ + ; \ + } \ +} + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ + __is_signed) \ + case attr_nr: + +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ + __get, __put, __is_signed) \ + case attr_nr: + +#include GENL_MAGIC_INCLUDE_FILE + +/* }}}1 + * Magic: declare structs + * struct <name> { + * fields + * }; + * {{{2 + */ + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +struct s_name { s_fields }; + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ + __is_signed) \ + type name; + +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ + __get, __put, __is_signed) \ + type name[maxlen]; \ + __u32 name ## _len; + +#include GENL_MAGIC_INCLUDE_FILE + +#undef GENL_struct +#define GENL_struct(tag_name, tag_number, s_name, s_fields) \ +enum { \ + s_fields \ +}; + +#undef __field +#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put, \ + is_signed) \ + F_ ## name ## _IS_SIGNED = is_signed, + +#undef __array +#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, \ + __get, __put, is_signed) \ + F_ ## name ## _IS_SIGNED = is_signed, + +#include GENL_MAGIC_INCLUDE_FILE + +/* }}}1 */ +#endif /* GENL_MAGIC_STRUCT_H */ +/* vim: set foldmethod=marker nofoldenable : */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f74856e..0f615eb 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,6 +30,7 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u +#define ___GFP_KMEMCG 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -89,6 +90,7 @@ struct vm_area_struct; #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */ +#define __GFP_KMEMCG ((__force gfp_t)___GFP_KMEMCG) /* Allocation comes from a memcg-accounted resource */ #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */ /* @@ -365,6 +367,9 @@ 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_memcg_kmem_pages(struct page *page, unsigned int order); +extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order); + #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index d73878c..ce8217f 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -62,7 +62,7 @@ extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); -extern int hugetlb_cgroup_file_init(int idx) __init; +extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage); @@ -111,9 +111,8 @@ hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, return; } -static inline int __init hugetlb_cgroup_file_init(int idx) +static inline void hugetlb_cgroup_file_init(void) { - return 0; } static inline void hugetlb_cgroup_migrate(struct page *oldhpage, diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h index 92a0dc7..babe0cf 100644 --- a/include/linux/i2c-omap.h +++ b/include/linux/i2c-omap.h @@ -20,8 +20,6 @@ #define OMAP_I2C_FLAG_NO_FIFO BIT(0) #define OMAP_I2C_FLAG_SIMPLE_CLOCK BIT(1) #define OMAP_I2C_FLAG_16BIT_DATA_REG BIT(2) -#define OMAP_I2C_FLAG_RESET_REGS_POSTIDLE BIT(3) -#define OMAP_I2C_FLAG_APPLY_ERRATA_I207 BIT(4) #define OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK BIT(5) #define OMAP_I2C_FLAG_FORCE_19200_INT_CLK BIT(6) /* how the CPU address bus must be translated for I2C unit access */ diff --git a/include/linux/i2c/i2c-sh_mobile.h b/include/linux/i2c/i2c-sh_mobile.h index beda708..06e3089 100644 --- a/include/linux/i2c/i2c-sh_mobile.h +++ b/include/linux/i2c/i2c-sh_mobile.h @@ -5,6 +5,7 @@ struct i2c_sh_mobile_platform_data { unsigned long bus_speed; + unsigned int clks_per_count; }; #endif /* __I2C_SH_MOBILE_H__ */ diff --git a/include/linux/idr.h b/include/linux/idr.h index 87259a4..de7e190 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -152,4 +152,15 @@ void ida_simple_remove(struct ida *ida, unsigned int id); void __init idr_init_cache(void); +/** + * idr_for_each_entry - iterate over an idr's elements of a given type + * @idp: idr handle + * @entry: the type * to use as cursor + * @id: id entry's key + */ +#define idr_for_each_entry(idp, entry, id) \ + for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ + entry != NULL; \ + ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) + #endif /* __IDR_H__ */ diff --git a/include/linux/ima.h b/include/linux/ima.h index 2c7223d..86c361e 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,6 +18,7 @@ extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_module_check(struct file *file); #else static inline int ima_bprm_check(struct linux_binprm *bprm) @@ -40,6 +41,11 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } +static inline int ima_module_check(struct file *file) +{ + return 0; +} + #endif /* CONFIG_IMA_H */ #ifdef CONFIG_IMA_APPRAISE diff --git a/include/linux/init.h b/include/linux/init.h index f63692d..a799273 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -182,16 +182,16 @@ extern bool initcall_debug; * can point at the same handler without causing duplicate-symbol build errors. */ -#define __define_initcall(level,fn,id) \ +#define __define_initcall(fn, id) \ static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(".initcall" level ".init"))) = fn + __attribute__((__section__(".initcall" #id ".init"))) = fn /* * Early initcalls run before initializing SMP. * * Only for built-in code, not modules. */ -#define early_initcall(fn) __define_initcall("early",fn,early) +#define early_initcall(fn) __define_initcall(fn, early) /* * A "pure" initcall has no dependencies on anything else, and purely @@ -200,23 +200,23 @@ extern bool initcall_debug; * This only exists for built-in code, not for modules. * Keep main.c:initcall_level_names[] in sync. */ -#define pure_initcall(fn) __define_initcall("0",fn,0) - -#define core_initcall(fn) __define_initcall("1",fn,1) -#define core_initcall_sync(fn) __define_initcall("1s",fn,1s) -#define postcore_initcall(fn) __define_initcall("2",fn,2) -#define postcore_initcall_sync(fn) __define_initcall("2s",fn,2s) -#define arch_initcall(fn) __define_initcall("3",fn,3) -#define arch_initcall_sync(fn) __define_initcall("3s",fn,3s) -#define subsys_initcall(fn) __define_initcall("4",fn,4) -#define subsys_initcall_sync(fn) __define_initcall("4s",fn,4s) -#define fs_initcall(fn) __define_initcall("5",fn,5) -#define fs_initcall_sync(fn) __define_initcall("5s",fn,5s) -#define rootfs_initcall(fn) __define_initcall("rootfs",fn,rootfs) -#define device_initcall(fn) __define_initcall("6",fn,6) -#define device_initcall_sync(fn) __define_initcall("6s",fn,6s) -#define late_initcall(fn) __define_initcall("7",fn,7) -#define late_initcall_sync(fn) __define_initcall("7s",fn,7s) +#define pure_initcall(fn) __define_initcall(fn, 0) + +#define core_initcall(fn) __define_initcall(fn, 1) +#define core_initcall_sync(fn) __define_initcall(fn, 1s) +#define postcore_initcall(fn) __define_initcall(fn, 2) +#define postcore_initcall_sync(fn) __define_initcall(fn, 2s) +#define arch_initcall(fn) __define_initcall(fn, 3) +#define arch_initcall_sync(fn) __define_initcall(fn, 3s) +#define subsys_initcall(fn) __define_initcall(fn, 4) +#define subsys_initcall_sync(fn) __define_initcall(fn, 4s) +#define fs_initcall(fn) __define_initcall(fn, 5) +#define fs_initcall_sync(fn) __define_initcall(fn, 5s) +#define rootfs_initcall(fn) __define_initcall(fn, rootfs) +#define device_initcall(fn) __define_initcall(fn, 6) +#define device_initcall_sync(fn) __define_initcall(fn, 6s) +#define late_initcall(fn) __define_initcall(fn, 7) +#define late_initcall_sync(fn) __define_initcall(fn, 7s) #define __initcall(fn) device_initcall(fn) diff --git a/include/linux/input.h b/include/linux/input.h index cab994b..82ce323 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -112,6 +112,11 @@ struct input_value { * @h_list: list of input handles associated with the device. When * accessing the list dev->mutex must be held * @node: used to place the device onto input_dev_list + * @num_vals: number of values queued in the current frame + * @max_vals: maximum number of values queued in a frame + * @vals: array of values queued in the current frame + * @devres_managed: indicates that devices is managed with devres framework + * and needs not be explicitly unregistered or freed. */ struct input_dev { const char *name; @@ -180,6 +185,8 @@ struct input_dev { unsigned int num_vals; unsigned int max_vals; struct input_value *vals; + + bool devres_managed; }; #define to_input_dev(d) container_of(d, struct input_dev, dev) @@ -323,7 +330,8 @@ struct input_handle { struct list_head h_node; }; -struct input_dev *input_allocate_device(void); +struct input_dev __must_check *input_allocate_device(void); +struct input_dev __must_check *devm_input_allocate_device(struct device *); void input_free_device(struct input_dev *dev); static inline struct input_dev *input_get_device(struct input_dev *dev) diff --git a/include/linux/input/bu21013.h b/include/linux/input/bu21013.h index 05e0328..6230d76 100644 --- a/include/linux/input/bu21013.h +++ b/include/linux/input/bu21013.h @@ -9,13 +9,10 @@ /** * struct bu21013_platform_device - Handle the platform data - * @cs_en: pointer to the cs enable function - * @cs_dis: pointer to the cs disable function - * @irq_read_val: pointer to read the pen irq value function * @touch_x_max: touch x max * @touch_y_max: touch y max * @cs_pin: chip select pin - * @irq: irq pin + * @touch_pin: touch gpio pin * @ext_clk: external clock flag * @x_flip: x flip flag * @y_flip: y flip flag @@ -24,13 +21,10 @@ * This is used to handle the platform data */ struct bu21013_platform_device { - int (*cs_en)(int reset_pin); - int (*cs_dis)(int reset_pin); - int (*irq_read_val)(void); int touch_x_max; int touch_y_max; unsigned int cs_pin; - unsigned int irq; + unsigned int touch_pin; bool ext_clk; bool x_flip; bool y_flip; diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 5499c92..fe77197 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -67,6 +67,8 @@ struct ipc_namespace { /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; + + unsigned int proc_inum; }; extern struct ipc_namespace init_ipc_ns; @@ -133,7 +135,8 @@ static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #if defined(CONFIG_IPC_NS) extern struct ipc_namespace *copy_ipcs(unsigned long flags, - struct task_struct *tsk); + struct user_namespace *user_ns, struct ipc_namespace *ns); + static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) @@ -144,12 +147,12 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, - struct task_struct *tsk) + struct user_namespace *user_ns, struct ipc_namespace *ns) { if (flags & CLONE_NEWIPC) return ERR_PTR(-EINVAL); - return tsk->nsproxy->ipc_ns; + return ns; } static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d97ed58..d140e8f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -220,6 +220,23 @@ int __must_check _kstrtol(const char *s, unsigned int base, long *res); int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); int __must_check kstrtoll(const char *s, unsigned int base, long long *res); + +/** + * kstrtoul - convert a string to an unsigned long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign, but not a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Used as a replacement for the obsolete simple_strtoull. Return code must + * be checked. +*/ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) { /* @@ -233,6 +250,22 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign return _kstrtoul(s, base, res); } +/** + * kstrtol - convert a string to a long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign or a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Used as a replacement for the obsolete simple_strtoull. Return code must + * be checked. + */ static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) { /* diff --git a/include/linux/loop.h b/include/linux/loop.h index 6492181..460b60f 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -53,10 +53,13 @@ struct loop_device { spinlock_t lo_lock; struct bio_list lo_bio_list; + unsigned int lo_bio_count; int lo_state; struct mutex lo_ctl_mutex; struct task_struct *lo_thread; wait_queue_head_t lo_event; + /* wait queue for incoming requests */ + wait_queue_head_t lo_req_wait; struct request_queue *lo_queue; struct gendisk *lo_disk; diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index cafc7f9..4019013 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -166,9 +166,11 @@ struct lc_element { /* if we want to track a larger set of objects, * it needs to become arch independend u64 */ unsigned lc_number; - /* special label when on free list */ #define LC_FREE (~0U) + + /* for pending changes */ + unsigned lc_new_number; }; struct lru_cache { @@ -176,6 +178,7 @@ struct lru_cache { struct list_head lru; struct list_head free; struct list_head in_use; + struct list_head to_be_changed; /* the pre-created kmem cache to allocate the objects from */ struct kmem_cache *lc_cache; @@ -186,7 +189,7 @@ struct lru_cache { size_t element_off; /* number of elements (indices) */ - unsigned int nr_elements; + unsigned int nr_elements; /* Arbitrary limit on maximum tracked objects. Practical limit is much * lower due to allocation failures, probably. For typical use cases, * nr_elements should be a few thousand at most. @@ -194,18 +197,19 @@ struct lru_cache { * 8 high bits of .lc_index to be overloaded with flags in the future. */ #define LC_MAX_ACTIVE (1<<24) + /* allow to accumulate a few (index:label) changes, + * but no more than max_pending_changes */ + unsigned int max_pending_changes; + /* number of elements currently on to_be_changed list */ + unsigned int pending_changes; + /* statistics */ - unsigned used; /* number of lelements currently on in_use list */ - unsigned long hits, misses, starving, dirty, changed; + unsigned used; /* number of elements currently on in_use list */ + unsigned long hits, misses, starving, locked, changed; /* see below: flag-bits for lru_cache */ unsigned long flags; - /* when changing the label of an index element */ - unsigned int new_number; - - /* for paranoia when changing the label of an index element */ - struct lc_element *changing_element; void *lc_private; const char *name; @@ -221,10 +225,15 @@ enum { /* debugging aid, to catch concurrent access early. * user needs to guarantee exclusive access by proper locking! */ __LC_PARANOIA, - /* if we need to change the set, but currently there is a changing - * transaction pending, we are "dirty", and must deferr further - * changing requests */ + + /* annotate that the set is "dirty", possibly accumulating further + * changes, until a transaction is finally triggered */ __LC_DIRTY, + + /* Locked, no further changes allowed. + * Also used to serialize changing transactions. */ + __LC_LOCKED, + /* if we need to change the set, but currently there is no free nor * unused element available, we are "starving", and must not give out * further references, to guarantee that eventually some refcnt will @@ -236,9 +245,11 @@ enum { }; #define LC_PARANOIA (1<<__LC_PARANOIA) #define LC_DIRTY (1<<__LC_DIRTY) +#define LC_LOCKED (1<<__LC_LOCKED) #define LC_STARVING (1<<__LC_STARVING) extern struct lru_cache *lc_create(const char *name, struct kmem_cache *cache, + unsigned max_pending_changes, unsigned e_count, size_t e_size, size_t e_off); extern void lc_reset(struct lru_cache *lc); extern void lc_destroy(struct lru_cache *lc); @@ -249,7 +260,7 @@ extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr); extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e); -extern void lc_changed(struct lru_cache *lc, struct lc_element *e); +extern void lc_committed(struct lru_cache *lc); struct seq_file; extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc); @@ -258,32 +269,40 @@ extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char void (*detail) (struct seq_file *, struct lc_element *)); /** - * lc_try_lock - can be used to stop lc_get() from changing the tracked set + * lc_try_lock_for_transaction - can be used to stop lc_get() from changing the tracked set * @lc: the lru cache to operate on * - * Note that the reference counts and order on the active and lru lists may - * still change. Returns true if we acquired the lock. + * Allows (expects) the set to be "dirty". Note that the reference counts and + * order on the active and lru lists may still change. Used to serialize + * changing transactions. Returns true if we aquired the lock. */ -static inline int lc_try_lock(struct lru_cache *lc) +static inline int lc_try_lock_for_transaction(struct lru_cache *lc) { - return !test_and_set_bit(__LC_DIRTY, &lc->flags); + return !test_and_set_bit(__LC_LOCKED, &lc->flags); } /** + * lc_try_lock - variant to stop lc_get() from changing the tracked set + * @lc: the lru cache to operate on + * + * Note that the reference counts and order on the active and lru lists may + * still change. Only works on a "clean" set. Returns true if we aquired the + * lock, which means there are no pending changes, and any further attempt to + * change the set will not succeed until the next lc_unlock(). + */ +extern int lc_try_lock(struct lru_cache *lc); + +/** * lc_unlock - unlock @lc, allow lc_get() to change the set again * @lc: the lru cache to operate on */ static inline void lc_unlock(struct lru_cache *lc) { clear_bit(__LC_DIRTY, &lc->flags); - smp_mb__after_clear_bit(); + clear_bit_unlock(__LC_LOCKED, &lc->flags); } -static inline int lc_is_used(struct lru_cache *lc, unsigned int enr) -{ - struct lc_element *e = lc_find(lc, enr); - return e && e->refcnt; -} +extern bool lc_is_used(struct lru_cache *lc, unsigned int enr); #define lc_entry(ptr, type, member) \ container_of(ptr, type, member) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e98a74c..0108a56 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -21,11 +21,14 @@ #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> +#include <linux/hardirq.h> +#include <linux/jump_label.h> struct mem_cgroup; struct page_cgroup; struct page; struct mm_struct; +struct kmem_cache; /* Stats that can be updated by kernel. */ enum mem_cgroup_page_stat_item { @@ -414,5 +417,211 @@ static inline void sock_release_memcg(struct sock *sk) { } #endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */ + +#ifdef CONFIG_MEMCG_KMEM +extern struct static_key memcg_kmem_enabled_key; + +extern int memcg_limited_groups_array_size; + +/* + * Helper macro to loop through all memcg-specific caches. Callers must still + * check if the cache is valid (it is either valid or NULL). + * the slab_mutex must be held when looping through those caches + */ +#define for_each_memcg_cache_index(_idx) \ + for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++) + +static inline bool memcg_kmem_enabled(void) +{ + return static_key_false(&memcg_kmem_enabled_key); +} + +/* + * In general, we'll do everything in our power to not incur in any overhead + * for non-memcg users for the kmem functions. Not even a function call, if we + * can avoid it. + * + * Therefore, we'll inline all those functions so that in the best case, we'll + * see that kmemcg is off for everybody and proceed quickly. If it is on, + * we'll still do most of the flag checking inline. We check a lot of + * conditions, but because they are pretty simple, they are expected to be + * fast. + */ +bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, + int order); +void __memcg_kmem_commit_charge(struct page *page, + struct mem_cgroup *memcg, int order); +void __memcg_kmem_uncharge_pages(struct page *page, int order); + +int memcg_cache_id(struct mem_cgroup *memcg); +int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, + struct kmem_cache *root_cache); +void memcg_release_cache(struct kmem_cache *cachep); +void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep); + +int memcg_update_cache_size(struct kmem_cache *s, int num_groups); +void memcg_update_array_size(int num_groups); + +struct kmem_cache * +__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); + +void mem_cgroup_destroy_cache(struct kmem_cache *cachep); +void kmem_cache_destroy_memcg_children(struct kmem_cache *s); + +/** + * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. + * @gfp: the gfp allocation flags. + * @memcg: a pointer to the memcg this was charged against. + * @order: allocation order. + * + * returns true if the memcg where the current task belongs can hold this + * allocation. + * + * We return true automatically if this allocation is not to be accounted to + * any memcg. + */ +static inline bool +memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) +{ + if (!memcg_kmem_enabled()) + return true; + + /* + * __GFP_NOFAIL allocations will move on even if charging is not + * possible. Therefore we don't even try, and have this allocation + * unaccounted. We could in theory charge it with + * res_counter_charge_nofail, but we hope those allocations are rare, + * and won't be worth the trouble. + */ + if (!(gfp & __GFP_KMEMCG) || (gfp & __GFP_NOFAIL)) + return true; + if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) + return true; + + /* If the test is dying, just let it go. */ + if (unlikely(fatal_signal_pending(current))) + return true; + + return __memcg_kmem_newpage_charge(gfp, memcg, order); +} + +/** + * memcg_kmem_uncharge_pages: uncharge pages from memcg + * @page: pointer to struct page being freed + * @order: allocation order. + * + * there is no need to specify memcg here, since it is embedded in page_cgroup + */ +static inline void +memcg_kmem_uncharge_pages(struct page *page, int order) +{ + if (memcg_kmem_enabled()) + __memcg_kmem_uncharge_pages(page, order); +} + +/** + * memcg_kmem_commit_charge: embeds correct memcg in a page + * @page: pointer to struct page recently allocated + * @memcg: the memcg structure we charged against + * @order: allocation order. + * + * Needs to be called after memcg_kmem_newpage_charge, regardless of success or + * failure of the allocation. if @page is NULL, this function will revert the + * charges. Otherwise, it will commit the memcg given by @memcg to the + * corresponding page_cgroup. + */ +static inline void +memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) +{ + if (memcg_kmem_enabled() && memcg) + __memcg_kmem_commit_charge(page, memcg, order); +} + +/** + * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation + * @cachep: the original global kmem cache + * @gfp: allocation flags. + * + * This function assumes that the task allocating, which determines the memcg + * in the page allocator, belongs to the same cgroup throughout the whole + * process. Misacounting can happen if the task calls memcg_kmem_get_cache() + * while belonging to a cgroup, and later on changes. This is considered + * acceptable, and should only happen upon task migration. + * + * Before the cache is created by the memcg core, there is also a possible + * imbalance: the task belongs to a memcg, but the cache being allocated from + * is the global cache, since the child cache is not yet guaranteed to be + * ready. This case is also fine, since in this case the GFP_KMEMCG will not be + * passed and the page allocator will not attempt any cgroup accounting. + */ +static __always_inline struct kmem_cache * +memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) +{ + if (!memcg_kmem_enabled()) + return cachep; + if (gfp & __GFP_NOFAIL) + return cachep; + if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) + return cachep; + if (unlikely(fatal_signal_pending(current))) + return cachep; + + return __memcg_kmem_get_cache(cachep, gfp); +} +#else +#define for_each_memcg_cache_index(_idx) \ + for (; NULL; ) + +static inline bool memcg_kmem_enabled(void) +{ + return false; +} + +static inline bool +memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) +{ + return true; +} + +static inline void memcg_kmem_uncharge_pages(struct page *page, int order) +{ +} + +static inline void +memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) +{ +} + +static inline int memcg_cache_id(struct mem_cgroup *memcg) +{ + return -1; +} + +static inline int +memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, + struct kmem_cache *root_cache) +{ + return 0; +} + +static inline void memcg_release_cache(struct kmem_cache *cachep) +{ +} + +static inline void memcg_cache_list_add(struct mem_cgroup *memcg, + struct kmem_cache *s) +{ +} + +static inline struct kmem_cache * +memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) +{ + return cachep; +} + +static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7d9ebb7..f8f5162 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -128,10 +128,7 @@ struct page { }; struct list_head list; /* slobs list of pages */ - struct { /* slab fields */ - struct kmem_cache *slab_cache; - struct slab *slab_page; - }; + struct slab *slab_page; /* slab fields */ }; /* Remainder is not double word aligned */ @@ -146,7 +143,7 @@ struct page { #if USE_SPLIT_PTLOCKS spinlock_t ptl; #endif - struct kmem_cache *slab; /* SLUB: Pointer to slab */ + struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */ struct page *first_page; /* Compound tail pages */ }; diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 5a8e390..12b2ab5 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -4,9 +4,10 @@ struct mnt_namespace; struct fs_struct; +struct user_namespace; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, - struct fs_struct *); + struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); extern const struct file_operations proc_mounts_operations; diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index d6a5806..137b419 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -16,17 +16,15 @@ /* Chosen so that structs with an unsigned long line up. */ #define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long)) -#define ___module_cat(a,b) __mod_ ## a ## b -#define __module_cat(a,b) ___module_cat(a,b) #ifdef MODULE #define __MODULE_INFO(tag, name, info) \ -static const char __module_cat(name,__LINE__)[] \ +static const char __UNIQUE_ID(name)[] \ __used __attribute__((section(".modinfo"), unused, aligned(1))) \ = __stringify(tag) "=" info #else /* !MODULE */ /* This struct is here for syntactic coherency, it is not used */ #define __MODULE_INFO(tag, name, info) \ - struct __module_cat(name,__LINE__) {} + struct __UNIQUE_ID(name) {} #endif #define __MODULE_PARM_TYPE(name, _type) \ __MODULE_INFO(parmtype, name##type, #name ":" _type) diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index ed270bd..4eb0a50 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -23,6 +23,7 @@ #include <linux/mutex.h> #include <linux/kref.h> #include <linux/sysfs.h> +#include <linux/workqueue.h> struct hd_geometry; struct mtd_info; @@ -43,7 +44,8 @@ struct mtd_blktrans_dev { struct kref ref; struct gendisk *disk; struct attribute_group *disk_attributes; - struct task_struct *thread; + struct workqueue_struct *wq; + struct work_struct work; struct request_queue *rq; spinlock_t queue_lock; void *priv; diff --git a/include/linux/mtd/doc2000.h b/include/linux/mtd/doc2000.h index 0f6fea7..407d1e5 100644 --- a/include/linux/mtd/doc2000.h +++ b/include/linux/mtd/doc2000.h @@ -92,12 +92,26 @@ * Others use readb/writeb */ #if defined(__arm__) -#define ReadDOC_(adr, reg) ((unsigned char)(*(volatile __u32 *)(((unsigned long)adr)+((reg)<<2)))) -#define WriteDOC_(d, adr, reg) do{ *(volatile __u32 *)(((unsigned long)adr)+((reg)<<2)) = (__u32)d; wmb();} while(0) +static inline u8 ReadDOC_(u32 __iomem *addr, unsigned long reg) +{ + return __raw_readl(addr + reg); +} +static inline void WriteDOC_(u8 data, u32 __iomem *addr, unsigned long reg) +{ + __raw_writel(data, addr + reg); + wmb(); +} #define DOC_IOREMAP_LEN 0x8000 #elif defined(__ppc__) -#define ReadDOC_(adr, reg) ((unsigned char)(*(volatile __u16 *)(((unsigned long)adr)+((reg)<<1)))) -#define WriteDOC_(d, adr, reg) do{ *(volatile __u16 *)(((unsigned long)adr)+((reg)<<1)) = (__u16)d; wmb();} while(0) +static inline u8 ReadDOC_(u16 __iomem *addr, unsigned long reg) +{ + return __raw_readw(addr + reg); +} +static inline void WriteDOC_(u8 data, u16 __iomem *addr, unsigned long reg) +{ + __raw_writew(data, addr + reg); + wmb(); +} #define DOC_IOREMAP_LEN 0x4000 #else #define ReadDOC_(adr, reg) readb((void __iomem *)(adr) + (reg)) diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h index b200292..d6ed61e 100644 --- a/include/linux/mtd/fsmc.h +++ b/include/linux/mtd/fsmc.h @@ -155,9 +155,6 @@ struct fsmc_nand_platform_data { unsigned int width; unsigned int bank; - /* CLE, ALE offsets */ - unsigned int cle_off; - unsigned int ale_off; enum access_mode mode; void (*select_bank)(uint32_t bank, uint32_t busw); diff --git a/include/linux/mtd/gpmi-nand.h b/include/linux/mtd/gpmi-nand.h deleted file mode 100644 index ed3c4e0..0000000 --- a/include/linux/mtd/gpmi-nand.h +++ /dev/null @@ -1,68 +0,0 @@ -/* - * Copyright (C) 2011 Freescale Semiconductor, Inc. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef __MACH_MXS_GPMI_NAND_H__ -#define __MACH_MXS_GPMI_NAND_H__ - -/* The size of the resources is fixed. */ -#define GPMI_NAND_RES_SIZE 6 - -/* Resource names for the GPMI NAND driver. */ -#define GPMI_NAND_GPMI_REGS_ADDR_RES_NAME "gpmi-nand" -#define GPMI_NAND_GPMI_INTERRUPT_RES_NAME "GPMI NAND GPMI Interrupt" -#define GPMI_NAND_BCH_REGS_ADDR_RES_NAME "bch" -#define GPMI_NAND_BCH_INTERRUPT_RES_NAME "bch" -#define GPMI_NAND_DMA_CHANNELS_RES_NAME "GPMI NAND DMA Channels" -#define GPMI_NAND_DMA_INTERRUPT_RES_NAME "gpmi-dma" - -/** - * struct gpmi_nand_platform_data - GPMI NAND driver platform data. - * - * This structure communicates platform-specific information to the GPMI NAND - * driver that can't be expressed as resources. - * - * @platform_init: A pointer to a function the driver will call to - * initialize the platform (e.g., set up the pin mux). - * @min_prop_delay_in_ns: Minimum propagation delay of GPMI signals to and - * from the NAND Flash device, in nanoseconds. - * @max_prop_delay_in_ns: Maximum propagation delay of GPMI signals to and - * from the NAND Flash device, in nanoseconds. - * @max_chip_count: The maximum number of chips for which the driver - * should configure the hardware. This value most - * likely reflects the number of pins that are - * connected to a NAND Flash device. If this is - * greater than the SoC hardware can support, the - * driver will print a message and fail to initialize. - * @partitions: An optional pointer to an array of partition - * descriptions. - * @partition_count: The number of elements in the partitions array. - */ -struct gpmi_nand_platform_data { - /* SoC hardware information. */ - int (*platform_init)(void); - - /* NAND Flash information. */ - unsigned int min_prop_delay_in_ns; - unsigned int max_prop_delay_in_ns; - unsigned int max_chip_count; - - /* Medium information. */ - struct mtd_partition *partitions; - unsigned partition_count; -}; -#endif diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 3595a02..f6eb433 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -328,7 +328,7 @@ static inline int map_word_bitsset(struct map_info *map, map_word val1, map_word static inline map_word map_word_load(struct map_info *map, const void *ptr) { - map_word r; + map_word r = {{0} }; if (map_bankwidth_is_1(map)) r.x[0] = *(unsigned char *)ptr; @@ -391,7 +391,7 @@ static inline map_word map_word_ff(struct map_info *map) static inline map_word inline_map_read(struct map_info *map, unsigned long ofs) { - map_word r; + map_word uninitialized_var(r); if (map_bankwidth_is_1(map)) r.x[0] = __raw_readb(map->virt + ofs); diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 81d61e7..f9ac289 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -98,7 +98,7 @@ struct mtd_oob_ops { }; #define MTD_MAX_OOBFREE_ENTRIES_LARGE 32 -#define MTD_MAX_ECCPOS_ENTRIES_LARGE 448 +#define MTD_MAX_ECCPOS_ENTRIES_LARGE 640 /* * Internal ECC layout control structure. For historical reasons, there is a * similar, smaller struct nand_ecclayout_user (in mtd-abi.h) that is retained diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 24e9159..7ccb3c5 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -219,6 +219,13 @@ typedef enum { #define NAND_OWN_BUFFERS 0x00020000 /* Chip may not exist, so silence any errors in scan */ #define NAND_SCAN_SILENT_NODEV 0x00040000 +/* + * Autodetect nand buswidth with readid/onfi. + * This suppose the driver will configure the hardware in 8 bits mode + * when calling nand_scan_ident, and update its configuration + * before calling nand_scan_tail. + */ +#define NAND_BUSWIDTH_AUTO 0x00080000 /* Options set by nand scan */ /* Nand scan has allocated controller struct */ @@ -471,8 +478,8 @@ struct nand_buffers { * non 0 if ONFI supported. * @onfi_params: [INTERN] holds the ONFI page parameter when ONFI is * supported, 0 otherwise. - * @onfi_set_features [REPLACEABLE] set the features for ONFI nand - * @onfi_get_features [REPLACEABLE] get the features for ONFI nand + * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand + * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand * @ecclayout: [REPLACEABLE] the default ECC placement scheme * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index 01e4b15..1c28f88 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -20,6 +20,7 @@ #ifndef __SH_FLCTL_H__ #define __SH_FLCTL_H__ +#include <linux/completion.h> #include <linux/mtd/mtd.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> @@ -107,6 +108,7 @@ #define ESTERINTE (0x1 << 24) /* ECC error interrupt enable */ #define AC1CLR (0x1 << 19) /* ECC FIFO clear */ #define AC0CLR (0x1 << 18) /* Data FIFO clear */ +#define DREQ0EN (0x1 << 16) /* FLDTFIFODMA Request Enable */ #define ECERB (0x1 << 9) /* ECC error */ #define STERB (0x1 << 8) /* Status error */ #define STERINTE (0x1 << 4) /* Status error enable */ @@ -138,6 +140,8 @@ enum flctl_ecc_res_t { FL_TIMEOUT }; +struct dma_chan; + struct sh_flctl { struct mtd_info mtd; struct nand_chip chip; @@ -147,7 +151,7 @@ struct sh_flctl { uint8_t done_buff[2048 + 64]; /* max size 2048 + 64 */ int read_bytes; - int index; + unsigned int index; int seqin_column; /* column in SEQIN cmd */ int seqin_page_addr; /* page_addr in SEQIN cmd */ uint32_t seqin_read_cmd; /* read cmd in SEQIN cmd */ @@ -161,6 +165,11 @@ struct sh_flctl { unsigned hwecc:1; /* Hardware ECC (0 = disabled, 1 = enabled) */ unsigned holden:1; /* Hardware has FLHOLDCR and HOLDEN is set */ unsigned qos_request:1; /* QoS request to prevent deep power shutdown */ + + /* DMA related objects */ + struct dma_chan *chan_fifo0_rx; + struct dma_chan *chan_fifo0_tx; + struct completion dma_complete; }; struct sh_flctl_platform_data { @@ -170,6 +179,9 @@ struct sh_flctl_platform_data { unsigned has_hwecc:1; unsigned use_holden:1; + + unsigned int slave_id_fifo0_tx; + unsigned int slave_id_fifo0_rx; }; static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a9e76ee..6c6ed15 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -198,51 +198,4 @@ struct nfs_server { #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) - -/* maximum number of slots to use */ -#define NFS4_DEF_SLOT_TABLE_SIZE (16U) -#define NFS4_MAX_SLOT_TABLE (256U) -#define NFS4_NO_SLOT ((u32)-1) - -#if IS_ENABLED(CONFIG_NFS_V4) - -/* Sessions */ -#define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long)) -struct nfs4_slot_table { - struct nfs4_slot *slots; /* seqid per slot */ - unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */ - spinlock_t slot_tbl_lock; - struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */ - u32 max_slots; /* # slots in table */ - u32 highest_used_slotid; /* sent to server on each SEQ. - * op for dynamic resizing */ - u32 target_max_slots; /* Set by CB_RECALL_SLOT as - * the new max_slots */ - struct completion complete; -}; - -static inline int slot_idx(struct nfs4_slot_table *tbl, struct nfs4_slot *sp) -{ - return sp - tbl->slots; -} - -/* - * Session related parameters - */ -struct nfs4_session { - struct nfs4_sessionid sess_id; - u32 flags; - unsigned long session_state; - u32 hash_alg; - u32 ssv_len; - - /* The fore and back channel */ - struct nfs4_channel_attrs fc_attrs; - struct nfs4_slot_table fc_slot_table; - struct nfs4_channel_attrs bc_attrs; - struct nfs4_slot_table bc_slot_table; - struct nfs_client *clp; -}; - -#endif /* CONFIG_NFS_V4 */ #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a73ea89..29adb12 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -185,23 +185,20 @@ struct nfs4_channel_attrs { u32 max_reqs; }; -/* nfs41 sessions slot seqid */ -struct nfs4_slot { - u32 seq_nr; -}; - +struct nfs4_slot; struct nfs4_sequence_args { - struct nfs4_session *sa_session; - u32 sa_slotid; - u8 sa_cache_this; + struct nfs4_slot *sa_slot; + u8 sa_cache_this : 1, + sa_privileged : 1; }; struct nfs4_sequence_res { - struct nfs4_session *sr_session; struct nfs4_slot *sr_slot; /* slot used to send request */ + unsigned long sr_timestamp; int sr_status; /* sequence operation status */ - unsigned long sr_renewal_time; u32 sr_status_flags; + u32 sr_highest_slotid; + u32 sr_target_highest_slotid; }; struct nfs4_get_lease_time_args { @@ -209,8 +206,8 @@ struct nfs4_get_lease_time_args { }; struct nfs4_get_lease_time_res { - struct nfs_fsinfo *lr_fsinfo; struct nfs4_sequence_res lr_seq_res; + struct nfs_fsinfo *lr_fsinfo; }; #define PNFS_LAYOUT_MAXSIZE 4096 @@ -228,23 +225,23 @@ struct pnfs_layout_range { }; struct nfs4_layoutget_args { + struct nfs4_sequence_args seq_args; __u32 type; struct pnfs_layout_range range; __u64 minlength; __u32 maxcount; struct inode *inode; struct nfs_open_context *ctx; - struct nfs4_sequence_args seq_args; nfs4_stateid stateid; struct nfs4_layoutdriver_data layout; }; struct nfs4_layoutget_res { + struct nfs4_sequence_res seq_res; __u32 return_on_close; struct pnfs_layout_range range; __u32 type; nfs4_stateid stateid; - struct nfs4_sequence_res seq_res; struct nfs4_layoutdriver_data *layoutp; }; @@ -255,38 +252,38 @@ struct nfs4_layoutget { }; struct nfs4_getdevicelist_args { + struct nfs4_sequence_args seq_args; const struct nfs_fh *fh; u32 layoutclass; - struct nfs4_sequence_args seq_args; }; struct nfs4_getdevicelist_res { - struct pnfs_devicelist *devlist; struct nfs4_sequence_res seq_res; + struct pnfs_devicelist *devlist; }; struct nfs4_getdeviceinfo_args { - struct pnfs_device *pdev; struct nfs4_sequence_args seq_args; + struct pnfs_device *pdev; }; struct nfs4_getdeviceinfo_res { - struct pnfs_device *pdev; struct nfs4_sequence_res seq_res; + struct pnfs_device *pdev; }; struct nfs4_layoutcommit_args { + struct nfs4_sequence_args seq_args; nfs4_stateid stateid; __u64 lastbytewritten; struct inode *inode; const u32 *bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_layoutcommit_res { + struct nfs4_sequence_res seq_res; struct nfs_fattr *fattr; const struct nfs_server *server; - struct nfs4_sequence_res seq_res; int status; }; @@ -300,11 +297,11 @@ struct nfs4_layoutcommit_data { }; struct nfs4_layoutreturn_args { + struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; nfs4_stateid stateid; __u32 layout_type; - struct nfs4_sequence_args seq_args; }; struct nfs4_layoutreturn_res { @@ -330,6 +327,7 @@ struct stateowner_id { * Arguments to the open call. */ struct nfs_openargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; struct nfs_seqid * seqid; int open_flags; @@ -350,10 +348,10 @@ struct nfs_openargs { const u32 * bitmask; const u32 * open_bitmap; __u32 claim; - struct nfs4_sequence_args seq_args; }; struct nfs_openres { + struct nfs4_sequence_res seq_res; nfs4_stateid stateid; struct nfs_fh fh; struct nfs4_change_info cinfo; @@ -368,7 +366,6 @@ struct nfs_openres { __u32 attrset[NFS4_BITMAP_SIZE]; struct nfs4_string *owner; struct nfs4_string *group_owner; - struct nfs4_sequence_res seq_res; __u32 access_request; __u32 access_supported; __u32 access_result; @@ -392,20 +389,20 @@ struct nfs_open_confirmres { * Arguments to the close call. */ struct nfs_closeargs { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; nfs4_stateid * stateid; struct nfs_seqid * seqid; fmode_t fmode; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs_closeres { + struct nfs4_sequence_res seq_res; nfs4_stateid stateid; struct nfs_fattr * fattr; struct nfs_seqid * seqid; const struct nfs_server *server; - struct nfs4_sequence_res seq_res; }; /* * * Arguments to the lock,lockt, and locku call. @@ -417,6 +414,7 @@ struct nfs_lowner { }; struct nfs_lock_args { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * lock_seqid; @@ -427,40 +425,39 @@ struct nfs_lock_args { unsigned char block : 1; unsigned char reclaim : 1; unsigned char new_lock_owner : 1; - struct nfs4_sequence_args seq_args; }; struct nfs_lock_res { + struct nfs4_sequence_res seq_res; nfs4_stateid stateid; struct nfs_seqid * lock_seqid; struct nfs_seqid * open_seqid; - struct nfs4_sequence_res seq_res; }; struct nfs_locku_args { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * seqid; nfs4_stateid * stateid; - struct nfs4_sequence_args seq_args; }; struct nfs_locku_res { + struct nfs4_sequence_res seq_res; nfs4_stateid stateid; struct nfs_seqid * seqid; - struct nfs4_sequence_res seq_res; }; struct nfs_lockt_args { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; struct file_lock * fl; struct nfs_lowner lock_owner; - struct nfs4_sequence_args seq_args; }; struct nfs_lockt_res { - struct file_lock * denied; /* LOCK, LOCKT failed */ struct nfs4_sequence_res seq_res; + struct file_lock * denied; /* LOCK, LOCKT failed */ }; struct nfs_release_lockowner_args { @@ -468,22 +465,23 @@ struct nfs_release_lockowner_args { }; struct nfs4_delegreturnargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; const nfs4_stateid *stateid; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_delegreturnres { + struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; const struct nfs_server *server; - struct nfs4_sequence_res seq_res; }; /* * Arguments to the read call. */ struct nfs_readargs { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; struct nfs_open_context *context; struct nfs_lock_context *lock_context; @@ -491,20 +489,20 @@ struct nfs_readargs { __u32 count; unsigned int pgbase; struct page ** pages; - struct nfs4_sequence_args seq_args; }; struct nfs_readres { + struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; __u32 count; int eof; - struct nfs4_sequence_res seq_res; }; /* * Arguments to the write call. */ struct nfs_writeargs { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; struct nfs_open_context *context; struct nfs_lock_context *lock_context; @@ -514,7 +512,6 @@ struct nfs_writeargs { unsigned int pgbase; struct page ** pages; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs_write_verifier { @@ -527,65 +524,65 @@ struct nfs_writeverf { }; struct nfs_writeres { + struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; struct nfs_writeverf * verf; __u32 count; const struct nfs_server *server; - struct nfs4_sequence_res seq_res; }; /* * Arguments to the commit call. */ struct nfs_commitargs { + struct nfs4_sequence_args seq_args; struct nfs_fh *fh; __u64 offset; __u32 count; const u32 *bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs_commitres { + struct nfs4_sequence_res seq_res; struct nfs_fattr *fattr; struct nfs_writeverf *verf; const struct nfs_server *server; - struct nfs4_sequence_res seq_res; }; /* * Common arguments to the unlink call */ struct nfs_removeargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh *fh; struct qstr name; - struct nfs4_sequence_args seq_args; }; struct nfs_removeres { + struct nfs4_sequence_res seq_res; const struct nfs_server *server; struct nfs_fattr *dir_attr; struct nfs4_change_info cinfo; - struct nfs4_sequence_res seq_res; }; /* * Common arguments to the rename call */ struct nfs_renameargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh *old_dir; const struct nfs_fh *new_dir; const struct qstr *old_name; const struct qstr *new_name; - struct nfs4_sequence_args seq_args; }; struct nfs_renameres { + struct nfs4_sequence_res seq_res; const struct nfs_server *server; struct nfs4_change_info old_cinfo; struct nfs_fattr *old_fattr; struct nfs4_change_info new_cinfo; struct nfs_fattr *new_fattr; - struct nfs4_sequence_res seq_res; }; /* @@ -626,20 +623,20 @@ struct nfs_createargs { }; struct nfs_setattrargs { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; nfs4_stateid stateid; struct iattr * iap; const struct nfs_server * server; /* Needed for name mapping */ const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs_setaclargs { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; size_t acl_len; unsigned int acl_pgbase; struct page ** acl_pages; - struct nfs4_sequence_args seq_args; }; struct nfs_setaclres { @@ -647,27 +644,27 @@ struct nfs_setaclres { }; struct nfs_getaclargs { + struct nfs4_sequence_args seq_args; struct nfs_fh * fh; size_t acl_len; unsigned int acl_pgbase; struct page ** acl_pages; - struct nfs4_sequence_args seq_args; }; /* getxattr ACL interface flags */ #define NFS4_ACL_TRUNC 0x0001 /* ACL was truncated */ struct nfs_getaclres { + struct nfs4_sequence_res seq_res; size_t acl_len; size_t acl_data_offset; int acl_flags; struct page * acl_scratch; - struct nfs4_sequence_res seq_res; }; struct nfs_setattrres { + struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; const struct nfs_server * server; - struct nfs4_sequence_res seq_res; }; struct nfs_linkargs { @@ -832,21 +829,22 @@ struct nfs3_getaclres { typedef u64 clientid4; struct nfs4_accessargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; const u32 * bitmask; u32 access; - struct nfs4_sequence_args seq_args; }; struct nfs4_accessres { + struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; u32 supported; u32 access; - struct nfs4_sequence_res seq_res; }; struct nfs4_create_arg { + struct nfs4_sequence_args seq_args; u32 ftype; union { struct { @@ -863,88 +861,88 @@ struct nfs4_create_arg { const struct iattr * attrs; const struct nfs_fh * dir_fh; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_create_res { + struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fh * fh; struct nfs_fattr * fattr; struct nfs4_change_info dir_cinfo; - struct nfs4_sequence_res seq_res; }; struct nfs4_fsinfo_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_fsinfo_res { - struct nfs_fsinfo *fsinfo; struct nfs4_sequence_res seq_res; + struct nfs_fsinfo *fsinfo; }; struct nfs4_getattr_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_getattr_res { + struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_sequence_res seq_res; }; struct nfs4_link_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; const struct nfs_fh * dir_fh; const struct qstr * name; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_link_res { + struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; struct nfs4_change_info cinfo; struct nfs_fattr * dir_attr; - struct nfs4_sequence_res seq_res; }; struct nfs4_lookup_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * dir_fh; const struct qstr * name; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_lookup_res { + struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; struct nfs_fh * fh; - struct nfs4_sequence_res seq_res; }; struct nfs4_lookup_root_arg { - const u32 * bitmask; struct nfs4_sequence_args seq_args; + const u32 * bitmask; }; struct nfs4_pathconf_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_pathconf_res { - struct nfs_pathconf *pathconf; struct nfs4_sequence_res seq_res; + struct nfs_pathconf *pathconf; }; struct nfs4_readdir_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; u64 cookie; nfs4_verifier verifier; @@ -953,21 +951,20 @@ struct nfs4_readdir_arg { unsigned int pgbase; /* zero-copy data */ const u32 * bitmask; int plus; - struct nfs4_sequence_args seq_args; }; struct nfs4_readdir_res { + struct nfs4_sequence_res seq_res; nfs4_verifier verifier; unsigned int pgbase; - struct nfs4_sequence_res seq_res; }; struct nfs4_readlink { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; unsigned int pgbase; unsigned int pglen; /* zero-copy data */ struct page ** pages; /* zero-copy data */ - struct nfs4_sequence_args seq_args; }; struct nfs4_readlink_res { @@ -993,28 +990,28 @@ struct nfs4_setclientid_res { }; struct nfs4_statfs_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; const u32 * bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_statfs_res { - struct nfs_fsstat *fsstat; struct nfs4_sequence_res seq_res; + struct nfs_fsstat *fsstat; }; struct nfs4_server_caps_arg { - struct nfs_fh *fhandle; struct nfs4_sequence_args seq_args; + struct nfs_fh *fhandle; }; struct nfs4_server_caps_res { + struct nfs4_sequence_res seq_res; u32 attr_bitmask[3]; u32 acl_bitmask; u32 has_links; u32 has_symlinks; u32 fh_expire_type; - struct nfs4_sequence_res seq_res; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1040,16 +1037,16 @@ struct nfs4_fs_locations { }; struct nfs4_fs_locations_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh *dir_fh; const struct qstr *name; struct page *page; const u32 *bitmask; - struct nfs4_sequence_args seq_args; }; struct nfs4_fs_locations_res { - struct nfs4_fs_locations *fs_locations; struct nfs4_sequence_res seq_res; + struct nfs4_fs_locations *fs_locations; }; struct nfs4_secinfo_oid { @@ -1074,14 +1071,14 @@ struct nfs4_secinfo_flavors { }; struct nfs4_secinfo_arg { + struct nfs4_sequence_args seq_args; const struct nfs_fh *dir_fh; const struct qstr *name; - struct nfs4_sequence_args seq_args; }; struct nfs4_secinfo_res { - struct nfs4_secinfo_flavors *flavors; struct nfs4_sequence_res seq_res; + struct nfs4_secinfo_flavors *flavors; }; #endif /* CONFIG_NFS_V4 */ @@ -1161,9 +1158,9 @@ struct nfs41_create_session_res { }; struct nfs41_reclaim_complete_args { + struct nfs4_sequence_args seq_args; /* In the future extend to include curr_fh for use with migration */ unsigned char one_fs:1; - struct nfs4_sequence_args seq_args; }; struct nfs41_reclaim_complete_res { @@ -1173,28 +1170,28 @@ struct nfs41_reclaim_complete_res { #define SECINFO_STYLE_CURRENT_FH 0 #define SECINFO_STYLE_PARENT 1 struct nfs41_secinfo_no_name_args { - int style; struct nfs4_sequence_args seq_args; + int style; }; struct nfs41_test_stateid_args { - nfs4_stateid *stateid; struct nfs4_sequence_args seq_args; + nfs4_stateid *stateid; }; struct nfs41_test_stateid_res { - unsigned int status; struct nfs4_sequence_res seq_res; + unsigned int status; }; struct nfs41_free_stateid_args { - nfs4_stateid *stateid; struct nfs4_sequence_args seq_args; + nfs4_stateid *stateid; }; struct nfs41_free_stateid_res { - unsigned int status; struct nfs4_sequence_res seq_res; + unsigned int status; }; #else diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index cc37a55..10e5947 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -67,7 +67,7 @@ void exit_task_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, - struct fs_struct *); + struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) diff --git a/include/linux/of.h b/include/linux/of.h index 6cfea9a..5ebcc5c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -22,6 +22,7 @@ #include <linux/mod_devicetable.h> #include <linux/spinlock.h> #include <linux/topology.h> +#include <linux/notifier.h> #include <asm/byteorder.h> #include <asm/errno.h> @@ -282,16 +283,28 @@ extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_machine_is_compatible(const char *compat); -extern int prom_add_property(struct device_node* np, struct property* prop); -extern int prom_remove_property(struct device_node *np, struct property *prop); -extern int prom_update_property(struct device_node *np, - struct property *newprop); +extern int of_add_property(struct device_node *np, struct property *prop); +extern int of_remove_property(struct device_node *np, struct property *prop); +extern int of_update_property(struct device_node *np, struct property *newprop); -#if defined(CONFIG_OF_DYNAMIC) /* For updating the device tree at runtime */ -extern void of_attach_node(struct device_node *); -extern void of_detach_node(struct device_node *); -#endif +#define OF_RECONFIG_ATTACH_NODE 0x0001 +#define OF_RECONFIG_DETACH_NODE 0x0002 +#define OF_RECONFIG_ADD_PROPERTY 0x0003 +#define OF_RECONFIG_REMOVE_PROPERTY 0x0004 +#define OF_RECONFIG_UPDATE_PROPERTY 0x0005 + +struct of_prop_reconfig { + struct device_node *dn; + struct property *prop; +}; + +extern int of_reconfig_notifier_register(struct notifier_block *); +extern int of_reconfig_notifier_unregister(struct notifier_block *); +extern int of_reconfig_notify(unsigned long, void *); + +extern int of_attach_node(struct device_node *); +extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index b47d204..3863a4d 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -100,6 +100,7 @@ extern int of_platform_populate(struct device_node *root, #if !defined(CONFIG_OF_ADDRESS) struct of_dev_auxdata; +struct device; static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index bd1e860..3e88c9a 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -1,83 +1,34 @@ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H -#include <linux/mutex.h> +#include <linux/atomic.h> +#include <linux/rwsem.h> #include <linux/percpu.h> -#include <linux/rcupdate.h> -#include <linux/delay.h> +#include <linux/wait.h> +#include <linux/lockdep.h> struct percpu_rw_semaphore { - unsigned __percpu *counters; - bool locked; - struct mutex mtx; + unsigned int __percpu *fast_read_ctr; + atomic_t write_ctr; + struct rw_semaphore rw_sem; + atomic_t slow_read_ctr; + wait_queue_head_t write_waitq; }; -#define light_mb() barrier() -#define heavy_mb() synchronize_sched_expedited() +extern void percpu_down_read(struct percpu_rw_semaphore *); +extern void percpu_up_read(struct percpu_rw_semaphore *); -static inline void percpu_down_read(struct percpu_rw_semaphore *p) -{ - rcu_read_lock_sched(); - if (unlikely(p->locked)) { - rcu_read_unlock_sched(); - mutex_lock(&p->mtx); - this_cpu_inc(*p->counters); - mutex_unlock(&p->mtx); - return; - } - this_cpu_inc(*p->counters); - rcu_read_unlock_sched(); - light_mb(); /* A, between read of p->locked and read of data, paired with D */ -} +extern void percpu_down_write(struct percpu_rw_semaphore *); +extern void percpu_up_write(struct percpu_rw_semaphore *); -static inline void percpu_up_read(struct percpu_rw_semaphore *p) -{ - light_mb(); /* B, between read of the data and write to p->counter, paired with C */ - this_cpu_dec(*p->counters); -} +extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, + const char *, struct lock_class_key *); +extern void percpu_free_rwsem(struct percpu_rw_semaphore *); -static inline unsigned __percpu_count(unsigned __percpu *counters) -{ - unsigned total = 0; - int cpu; - - for_each_possible_cpu(cpu) - total += ACCESS_ONCE(*per_cpu_ptr(counters, cpu)); - - return total; -} - -static inline void percpu_down_write(struct percpu_rw_semaphore *p) -{ - mutex_lock(&p->mtx); - p->locked = true; - synchronize_sched_expedited(); /* make sure that all readers exit the rcu_read_lock_sched region */ - while (__percpu_count(p->counters)) - msleep(1); - heavy_mb(); /* C, between read of p->counter and write to data, paired with B */ -} - -static inline void percpu_up_write(struct percpu_rw_semaphore *p) -{ - heavy_mb(); /* D, between write to data and write to p->locked, paired with A */ - p->locked = false; - mutex_unlock(&p->mtx); -} - -static inline int percpu_init_rwsem(struct percpu_rw_semaphore *p) -{ - p->counters = alloc_percpu(unsigned); - if (unlikely(!p->counters)) - return -ENOMEM; - p->locked = false; - mutex_init(&p->mtx); - return 0; -} - -static inline void percpu_free_rwsem(struct percpu_rw_semaphore *p) -{ - free_percpu(p->counters); - p->counters = NULL; /* catch use after free bugs */ -} +#define percpu_init_rwsem(brw) \ +({ \ + static struct lock_class_key rwsem_key; \ + __percpu_init_rwsem(brw, #brw, &rwsem_key); \ +}) #endif diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 65e3e87..bf28599 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -21,6 +21,7 @@ struct pid_namespace { struct kref kref; struct pidmap pidmap[PIDMAP_ENTRIES]; int last_pid; + int nr_hashed; struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; @@ -31,9 +32,12 @@ struct pid_namespace { #ifdef CONFIG_BSD_PROCESS_ACCT struct bsd_acct_struct *bacct; #endif + struct user_namespace *user_ns; + struct work_struct proc_work; kgid_t pid_gid; int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ + unsigned int proc_inum; }; extern struct pid_namespace init_pid_ns; @@ -46,7 +50,8 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) return ns; } -extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns); +extern struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); @@ -59,8 +64,8 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) return ns; } -static inline struct pid_namespace * -copy_pid_ns(unsigned long flags, struct pid_namespace *ns) +static inline struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) ns = ERR_PTR(-EINVAL); diff --git a/include/linux/platform_data/i2c-cbus-gpio.h b/include/linux/platform_data/i2c-cbus-gpio.h new file mode 100644 index 0000000..6faa992 --- /dev/null +++ b/include/linux/platform_data/i2c-cbus-gpio.h @@ -0,0 +1,27 @@ +/* + * i2c-cbus-gpio.h - CBUS I2C platform_data definition + * + * Copyright (C) 2004-2009 Nokia Corporation + * + * Written by Felipe Balbi and Aaro Koskinen. + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file "COPYING" in the main directory of this + * archive for more details. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __INCLUDE_LINUX_I2C_CBUS_GPIO_H +#define __INCLUDE_LINUX_I2C_CBUS_GPIO_H + +struct i2c_cbus_platform_data { + int dat_gpio; + int clk_gpio; + int sel_gpio; +}; + +#endif /* __INCLUDE_LINUX_I2C_CBUS_GPIO_H */ diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h index 761f317..e81f62d 100644 --- a/include/linux/platform_data/lp855x.h +++ b/include/linux/platform_data/lp855x.h @@ -89,11 +89,6 @@ enum lp8556_brightness_source { LP8556_COMBINED2, /* pwm + i2c after the shaper block */ }; -struct lp855x_pwm_data { - void (*pwm_set_intensity) (int brightness, int max_brightness); - int (*pwm_get_intensity) (int max_brightness); -}; - struct lp855x_rom_data { u8 addr; u8 val; @@ -105,7 +100,7 @@ struct lp855x_rom_data { * @mode : brightness control by pwm or lp855x register * @device_control : value of DEVICE CONTROL register * @initial_brightness : initial value of backlight brightness - * @pwm_data : platform specific pwm generation functions. + * @period_ns : platform specific pwm period value. unit is nano. Only valid when mode is PWM_BASED. * @load_new_rom_data : 0 : use default configuration data @@ -118,7 +113,7 @@ struct lp855x_platform_data { enum lp855x_brightness_ctrl_mode mode; u8 device_control; int initial_brightness; - struct lp855x_pwm_data pwm_data; + unsigned int period_ns; u8 load_new_rom_data; int size_program; struct lp855x_rom_data *rom_data; diff --git a/include/linux/platform_data/mtd-nomadik-nand.h b/include/linux/platform_data/mtd-nomadik-nand.h deleted file mode 100644 index c3c8254..0000000 --- a/include/linux/platform_data/mtd-nomadik-nand.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef __ASM_ARCH_NAND_H -#define __ASM_ARCH_NAND_H - -struct nomadik_nand_platform_data { - struct mtd_partition *parts; - int nparts; - int options; - int (*init) (void); - int (*exit) (void); -}; - -#define NAND_IO_DATA 0x40000000 -#define NAND_IO_CMD 0x40800000 -#define NAND_IO_ADDR 0x41000000 - -#endif /* __ASM_ARCH_NAND_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 3fd2e87..32676b3 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -28,7 +28,11 @@ struct mm_struct; */ enum { - PROC_ROOT_INO = 1, + PROC_ROOT_INO = 1, + PROC_IPC_INIT_INO = 0xEFFFFFFFU, + PROC_UTS_INIT_INO = 0xEFFFFFFEU, + PROC_USER_INIT_INO = 0xEFFFFFFDU, + PROC_PID_INIT_INO = 0xEFFFFFFCU, }; /* @@ -174,7 +178,10 @@ extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent); extern struct file *proc_ns_fget(int fd); +extern bool proc_ns_inode(struct inode *inode); +extern int proc_alloc_inum(unsigned int *pino); +extern void proc_free_inum(unsigned int inum); #else #define proc_net_fops_create(net, name, mode, fops) ({ (void)(mode), NULL; }) @@ -229,6 +236,19 @@ static inline struct file *proc_ns_fget(int fd) return ERR_PTR(-EINVAL); } +static inline bool proc_ns_inode(struct inode *inode) +{ + return false; +} + +static inline int proc_alloc_inum(unsigned int *inum) +{ + *inum = 1; + return 0; +} +static inline void proc_free_inum(unsigned int inum) +{ +} #endif /* CONFIG_PROC_FS */ #if !defined(CONFIG_PROC_KCORE) @@ -247,10 +267,14 @@ struct proc_ns_operations { void *(*get)(struct task_struct *task); void (*put)(void *ns); int (*install)(struct nsproxy *nsproxy, void *ns); + unsigned int (*inum)(void *ns); }; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; extern const struct proc_ns_operations ipcns_operations; +extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations userns_operations; +extern const struct proc_ns_operations mntns_operations; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -290,4 +314,7 @@ static inline struct net *PDE_NET(struct proc_dir_entry *pde) return pde->parent->data; } +#include <linux/signal.h> + +void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set); #endif /* _LINUX_PROC_FS_H */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index a89ff04..addfbe7 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -32,6 +32,8 @@ #define PT_TRACE_EXIT PT_EVENT_FLAG(PTRACE_EVENT_EXIT) #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) +#define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) + /* single stepping state bits (used on ARM and PA-RISC) */ #define PT_SINGLESTEP_BIT 31 #define PT_SINGLESTEP (1<<PT_SINGLESTEP_BIT) diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 112b314..6d661f3 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -171,6 +171,9 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, unsigned int index, const char *label); +struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc, + const struct of_phandle_args *args); + struct pwm_device *pwm_get(struct device *dev, const char *consumer); void pwm_put(struct pwm_device *pwm); diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 640c69c..8dfaa2c 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -98,6 +98,9 @@ extern const struct raid6_calls raid6_altivec1; extern const struct raid6_calls raid6_altivec2; extern const struct raid6_calls raid6_altivec4; extern const struct raid6_calls raid6_altivec8; +extern const struct raid6_calls raid6_avx2x1; +extern const struct raid6_calls raid6_avx2x2; +extern const struct raid6_calls raid6_avx2x4; struct raid6_recov_calls { void (*data2)(int, size_t, int, int, void **); @@ -109,6 +112,7 @@ struct raid6_recov_calls { extern const struct raid6_recov_calls raid6_recov_intx1; extern const struct raid6_recov_calls raid6_recov_ssse3; +extern const struct raid6_recov_calls raid6_recov_avx2; /* Algorithm list */ extern const struct raid6_calls * const raid6_algos[]; diff --git a/include/linux/random.h b/include/linux/random.h index 6330ed4..d984608 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -25,10 +25,19 @@ extern const struct file_operations random_fops, urandom_fops; unsigned int get_random_int(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); -u32 random32(void); -void srandom32(u32 seed); +u32 prandom_u32(void); +void prandom_bytes(void *buf, int nbytes); +void prandom_seed(u32 seed); -u32 prandom32(struct rnd_state *); +/* + * These macros are preserved for backward compatibility and should be + * removed as soon as a transition is finished. + */ +#define random32() prandom_u32() +#define srandom32(seed) prandom_seed(seed) + +u32 prandom_u32_state(struct rnd_state *); +void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes); /* * Handle minimum values for seeds @@ -39,11 +48,11 @@ static inline u32 __seed(u32 x, u32 m) } /** - * prandom32_seed - set seed for prandom32(). + * prandom_seed_state - set seed for prandom_u32_state(). * @state: pointer to state structure to receive the seed. * @seed: arbitrary 64-bit value to use as a seed. */ -static inline void prandom32_seed(struct rnd_state *state, u64 seed) +static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { u32 i = (seed >> 32) ^ (seed << 10) ^ seed; diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 6f54e40..5ae8456 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -125,14 +125,16 @@ int res_counter_charge_nofail(struct res_counter *counter, * * these calls check for usage underflow and show a warning on the console * _locked call expects the counter->lock to be taken + * + * returns the total charges still present in @counter. */ -void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); -void res_counter_uncharge(struct res_counter *counter, unsigned long val); +u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); +u64 res_counter_uncharge(struct res_counter *counter, unsigned long val); -void res_counter_uncharge_until(struct res_counter *counter, - struct res_counter *top, - unsigned long val); +u64 res_counter_uncharge_until(struct res_counter *counter, + struct res_counter *top, + unsigned long val); /** * res_counter_margin - calculate chargeable space of a counter * @cnt: the counter diff --git a/include/linux/sched.h b/include/linux/sched.h index b089c92..f712465 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1597,6 +1597,7 @@ struct task_struct { unsigned long nr_pages; /* uncharged usage */ unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; + unsigned int memcg_kmem_skip_account; #endif #ifdef CONFIG_HAVE_HW_BREAKPOINT atomic_t ptrace_bp_refcnt; @@ -1778,12 +1779,6 @@ static inline int is_global_init(struct task_struct *tsk) return tsk->pid == 1; } -/* - * is_container_init: - * check whether in the task is init in its own pid namespace. - */ -extern int is_container_init(struct task_struct *tsk); - extern struct pid *cad_pid; extern void free_task(struct task_struct *tsk); diff --git a/include/linux/security.h b/include/linux/security.h index 05e88bd..0f6afc6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -694,6 +694,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * userspace to load a kernel module with the given name. * @kmod_name name of the module requested by the kernel * Return 0 if successful. + * @kernel_module_from_file: + * Load a kernel module from userspace. + * @file contains the file structure pointing to the file containing + * the kernel module to load. If the module is being loaded from a blob, + * this argument will be NULL. + * Return 0 if permission is granted. * @task_fix_setuid: * Update the module's state after setting one or more of the user * identity attributes of the current process. The @flags parameter @@ -1508,6 +1514,7 @@ struct security_operations { int (*kernel_act_as)(struct cred *new, u32 secid); int (*kernel_create_files_as)(struct cred *new, struct inode *inode); int (*kernel_module_request)(char *kmod_name); + int (*kernel_module_from_file)(struct file *file); int (*task_fix_setuid) (struct cred *new, const struct cred *old, int flags); int (*task_setpgid) (struct task_struct *p, pid_t pgid); @@ -1765,6 +1772,7 @@ void security_transfer_creds(struct cred *new, const struct cred *old); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); +int security_kernel_module_from_file(struct file *file); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags); int security_task_setpgid(struct task_struct *p, pid_t pgid); @@ -2278,6 +2286,11 @@ static inline int security_kernel_module_request(char *kmod_name) return 0; } +static inline int security_kernel_module_from_file(struct file *file) +{ + return 0; +} + static inline int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) diff --git a/include/linux/slab.h b/include/linux/slab.h index 83d1a14..5d168d7 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -11,6 +11,8 @@ #include <linux/gfp.h> #include <linux/types.h> +#include <linux/workqueue.h> + /* * Flags to pass to kmem_cache_create(). @@ -116,6 +118,7 @@ struct kmem_cache { }; #endif +struct mem_cgroup; /* * struct kmem_cache related prototypes */ @@ -125,10 +128,12 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); +struct kmem_cache * +kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t, + unsigned long, void (*)(void *), struct kmem_cache *); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); -unsigned int kmem_cache_size(struct kmem_cache *); /* * Please use this macro to create slab caches. Simply specify the @@ -176,6 +181,48 @@ unsigned int kmem_cache_size(struct kmem_cache *); #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif +/* + * This is the main placeholder for memcg-related information in kmem caches. + * struct kmem_cache will hold a pointer to it, so the memory cost while + * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it + * would otherwise be if that would be bundled in kmem_cache: we'll need an + * extra pointer chase. But the trade off clearly lays in favor of not + * penalizing non-users. + * + * Both the root cache and the child caches will have it. For the root cache, + * this will hold a dynamically allocated array large enough to hold + * information about the currently limited memcgs in the system. + * + * Child caches will hold extra metadata needed for its operation. Fields are: + * + * @memcg: pointer to the memcg this cache belongs to + * @list: list_head for the list of all caches in this memcg + * @root_cache: pointer to the global, root cache, this cache was derived from + * @dead: set to true after the memcg dies; the cache may still be around. + * @nr_pages: number of pages that belongs to this cache. + * @destroy: worker to be called whenever we are ready, or believe we may be + * ready, to destroy this cache. + */ +struct memcg_cache_params { + bool is_root_cache; + union { + struct kmem_cache *memcg_caches[0]; + struct { + struct mem_cgroup *memcg; + struct list_head list; + struct kmem_cache *root_cache; + bool dead; + atomic_t nr_pages; + struct work_struct destroy; + }; + }; +}; + +int memcg_update_all_caches(int num_memcgs); + +struct seq_file; +int cache_show(struct kmem_cache *s, struct seq_file *m); +void print_slabinfo_header(struct seq_file *m); /* * Common kmalloc functions provided by all allocators @@ -388,6 +435,14 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) return kmalloc_node(size, flags | __GFP_ZERO, node); } +/* + * Determine the size of a slab object + */ +static inline unsigned int kmem_cache_size(struct kmem_cache *s) +{ + return s->object_size; +} + void __init kmem_cache_init_late(void); #endif /* _LINUX_SLAB_H */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index cc290f0..8bb6e0e 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -81,6 +81,9 @@ struct kmem_cache { */ int obj_offset; #endif /* CONFIG_DEBUG_SLAB */ +#ifdef CONFIG_MEMCG_KMEM + struct memcg_cache_params *memcg_params; +#endif /* 6) per-cpu/per-node data, touched during every alloc/free */ /* @@ -89,9 +92,13 @@ struct kmem_cache { * (see kmem_cache_init()) * We still use [NR_CPUS] and not [1] or [0] because cache_cache * is statically defined, so we reserve the max number of cpus. + * + * We also need to guarantee that the list is able to accomodate a + * pointer for each node since "nodelists" uses the remainder of + * available pointers. */ struct kmem_list3 **nodelists; - struct array_cache *array[NR_CPUS]; + struct array_cache *array[NR_CPUS + MAX_NUMNODES]; /* * Do not add fields after array[] */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index df448ad..9db4825 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -101,6 +101,10 @@ struct kmem_cache { #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ #endif +#ifdef CONFIG_MEMCG_KMEM + struct memcg_cache_params *memcg_params; + int max_attr_size; /* for propagation, maximum size of a stored attr */ +#endif #ifdef CONFIG_NUMA /* @@ -222,7 +226,10 @@ void *__kmalloc(size_t size, gfp_t flags); static __always_inline void * kmalloc_order(size_t size, gfp_t flags, unsigned int order) { - void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order); + void *ret; + + flags |= (__GFP_COMP | __GFP_KMEMCG); + ret = (void *) __get_free_pages(flags, order); kmemleak_alloc(ret, size, 1, flags); return ret; } diff --git a/include/linux/string.h b/include/linux/string.h index 6301258..ac889c5 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -143,4 +143,15 @@ static inline bool strstarts(const char *str, const char *prefix) extern size_t memweight(const void *ptr, size_t bytes); +/** + * kbasename - return the last part of a pathname. + * + * @path: path to extract the filename from. + */ +static inline const char *kbasename(const char *path) +{ + const char *tail = strrchr(path, '/'); + return tail ? tail + 1 : path; +} + #endif /* _LINUX_STRING_H_ */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index dc0c3cc..b64f8eb 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -192,7 +192,6 @@ struct rpc_wait_queue { pid_t owner; /* process id of last task serviced */ unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ - unsigned char count; /* # task groups remaining serviced so far */ unsigned char nr; /* # tasks remaining for cookie */ unsigned short qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 91835e7..6caee34 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -560,10 +560,10 @@ asmlinkage long sys_utime(char __user *filename, asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes); asmlinkage long sys_lseek(unsigned int fd, off_t offset, - unsigned int origin); + unsigned int whence); asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high, unsigned long offset_low, loff_t __user *result, - unsigned int origin); + unsigned int whence); asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count); asmlinkage long sys_readahead(int fd, loff_t offset, size_t count); asmlinkage long sys_readv(unsigned long fd, @@ -880,4 +880,5 @@ asmlinkage long sys_process_vm_writev(pid_t pid, asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1, unsigned long idx2); +asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags); #endif diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ccc1899..e7e0473 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -61,6 +61,8 @@ extern long do_no_restart_syscall(struct restart_block *parm); # define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK) #endif +#define THREADINFO_GFP_ACCOUNTED (THREADINFO_GFP | __GFP_KMEMCG) + /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 9bbeabf..bd45eb7 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -69,6 +69,7 @@ struct usbnet { # define EVENT_DEV_ASLEEP 6 # define EVENT_DEV_OPEN 7 # define EVENT_DEVICE_REPORT_IDLE 8 +# define EVENT_NO_RUNTIME_PM 9 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) @@ -240,4 +241,6 @@ extern void usbnet_set_msglevel(struct net_device *, u32); extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *); extern int usbnet_nway_reset(struct net_device *net); +extern int usbnet_manage_power(struct usbnet *, int); + #endif /* __LINUX_USB_USBNET_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 95142ca..b9bd2e6 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -25,6 +25,7 @@ struct user_namespace { struct user_namespace *parent; kuid_t owner; kgid_t group; + unsigned int proc_inum; }; extern struct user_namespace init_user_ns; @@ -39,6 +40,7 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns) } extern int create_user_ns(struct cred *new); +extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void free_user_ns(struct kref *kref); static inline void put_user_ns(struct user_namespace *ns) @@ -66,6 +68,14 @@ static inline int create_user_ns(struct cred *new) return -EINVAL; } +static inline int unshare_userns(unsigned long unshare_flags, + struct cred **new_cred) +{ + if (unshare_flags & CLONE_NEWUSER) + return -EINVAL; + return 0; +} + static inline void put_user_ns(struct user_namespace *ns) { } diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 2b34520..239e277 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -23,6 +23,7 @@ struct uts_namespace { struct kref kref; struct new_utsname name; struct user_namespace *user_ns; + unsigned int proc_inum; }; extern struct uts_namespace init_uts_ns; @@ -33,7 +34,7 @@ static inline void get_uts_ns(struct uts_namespace *ns) } extern struct uts_namespace *copy_utsname(unsigned long flags, - struct task_struct *tsk); + struct user_namespace *user_ns, struct uts_namespace *old_ns); extern void free_uts_ns(struct kref *kref); static inline void put_uts_ns(struct uts_namespace *ns) @@ -50,12 +51,12 @@ static inline void put_uts_ns(struct uts_namespace *ns) } static inline struct uts_namespace *copy_utsname(unsigned long flags, - struct task_struct *tsk) + struct user_namespace *user_ns, struct uts_namespace *old_ns) { if (flags & CLONE_NEWUTS) return ERR_PTR(-EINVAL); - return tsk->nsproxy->uts_ns; + return old_ns; } #endif diff --git a/include/linux/wait.h b/include/linux/wait.h index 168dfe1..7cb64d4 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -550,6 +550,170 @@ do { \ __ret; \ }) + +#define __wait_event_lock_irq(wq, condition, lock, cmd) \ +do { \ + DEFINE_WAIT(__wait); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ + spin_lock_irq(&lock); \ + } \ + finish_wait(&wq, &__wait); \ +} while (0) + +/** + * wait_event_lock_irq_cmd - sleep until a condition gets true. The + * condition is checked under the lock. This + * is expected to be called with the lock + * taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before cmd + * and schedule() and reacquired afterwards. + * @cmd: a command which is invoked outside the critical section before + * sleep + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before invoking the cmd and going to sleep and is reacquired + * afterwards. + */ +#define wait_event_lock_irq_cmd(wq, condition, lock, cmd) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq, condition, lock, cmd); \ +} while (0) + +/** + * wait_event_lock_irq - sleep until a condition gets true. The + * condition is checked under the lock. This + * is expected to be called with the lock + * taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before schedule() + * and reacquired afterwards. + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before going to sleep and is reacquired afterwards. + */ +#define wait_event_lock_irq(wq, condition, lock) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq, condition, lock, ); \ +} while (0) + + +#define __wait_event_interruptible_lock_irq(wq, condition, \ + lock, ret, cmd) \ +do { \ + DEFINE_WAIT(__wait); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ + spin_lock_irq(&lock); \ + } \ + finish_wait(&wq, &__wait); \ +} while (0) + +/** + * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. + * The condition is checked under the lock. This is expected to + * be called with the lock taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before cmd and + * schedule() and reacquired afterwards. + * @cmd: a command which is invoked outside the critical section before + * sleep + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. The @condition is + * checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before invoking the cmd and going to sleep and is reacquired + * afterwards. + * + * The macro will return -ERESTARTSYS if it was interrupted by a signal + * and 0 if @condition evaluated to true. + */ +#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd) \ +({ \ + int __ret = 0; \ + \ + if (!(condition)) \ + __wait_event_interruptible_lock_irq(wq, condition, \ + lock, __ret, cmd); \ + __ret; \ +}) + +/** + * wait_event_interruptible_lock_irq - sleep until a condition gets true. + * The condition is checked under the lock. This is expected + * to be called with the lock taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before schedule() + * and reacquired afterwards. + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or signal is received. The @condition is + * checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before going to sleep and is reacquired afterwards. + * + * The macro will return -ERESTARTSYS if it was interrupted by a signal + * and 0 if @condition evaluated to true. + */ +#define wait_event_interruptible_lock_irq(wq, condition, lock) \ +({ \ + int __ret = 0; \ + \ + if (!(condition)) \ + __wait_event_interruptible_lock_irq(wq, condition, \ + lock, __ret, ); \ + __ret; \ +}) + + /* * These are the old interfaces to sleep waiting for an event. * They are racy. DO NOT use them, use the wait_event* interfaces above. |