diff options
Diffstat (limited to 'include')
83 files changed, 4513 insertions, 542 deletions
diff --git a/include/asm-generic/hardirq.h b/include/asm-generic/hardirq.h index 62f59080e5cc..04d0a977cd43 100644 --- a/include/asm-generic/hardirq.h +++ b/include/asm-generic/hardirq.h @@ -3,13 +3,13 @@ #include <linux/cache.h> #include <linux/threads.h> -#include <linux/irq.h> typedef struct { unsigned int __softirq_pending; } ____cacheline_aligned irq_cpustat_t; #include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */ +#include <linux/irq.h> #ifndef ack_bad_irq static inline void ack_bad_irq(unsigned int irq) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index e2bd73e8f9c0..f4d4120e5128 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -129,6 +129,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres #define move_pte(pte, prot, old_addr, new_addr) (pte) #endif +#ifndef flush_tlb_fix_spurious_fault +#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#endif + #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8a92a170fb7d..f4229fb315e1 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -220,6 +220,8 @@ \ BUG_TABLE \ \ + JUMP_TABLE \ + \ /* PCI quirks */ \ .pci_fixup : AT(ADDR(.pci_fixup) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_pci_fixups_early) = .; \ @@ -563,6 +565,14 @@ #define BUG_TABLE #endif +#define JUMP_TABLE \ + . = ALIGN(8); \ + __jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) { \ + VMLINUX_SYMBOL(__start___jump_table) = .; \ + *(__jump_table) \ + VMLINUX_SYMBOL(__stop___jump_table) = .; \ + } + #ifdef CONFIG_PM_TRACE #define TRACEDATA \ . = ALIGN(4); \ @@ -677,7 +687,9 @@ - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__per_cpu_start) = .; \ *(.data..percpu..first) \ + . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ + *(.data..percpu..readmostly) \ *(.data..percpu) \ *(.data..percpu..shared_aligned) \ VMLINUX_SYMBOL(__per_cpu_end) = .; \ @@ -703,7 +715,9 @@ VMLINUX_SYMBOL(__per_cpu_load) = .; \ VMLINUX_SYMBOL(__per_cpu_start) = .; \ *(.data..percpu..first) \ + . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ + *(.data..percpu..readmostly) \ *(.data..percpu) \ *(.data..percpu..shared_aligned) \ VMLINUX_SYMBOL(__per_cpu_end) = .; \ diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h index 7e3d2859be50..1d0ef1ae8036 100644 --- a/include/linux/acpi_pmtmr.h +++ b/include/linux/acpi_pmtmr.h @@ -25,8 +25,6 @@ static inline u32 acpi_pm_read_early(void) return acpi_pm_read_verified() & ACPI_PM_MASK; } -extern void pmtimer_wait(unsigned); - #else static inline u32 acpi_pm_read_early(void) diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h new file mode 100644 index 000000000000..7fff521d7eb5 --- /dev/null +++ b/include/linux/ceph/auth.h @@ -0,0 +1,92 @@ +#ifndef _FS_CEPH_AUTH_H +#define _FS_CEPH_AUTH_H + +#include <linux/ceph/types.h> +#include <linux/ceph/buffer.h> + +/* + * Abstract interface for communicating with the authenticate module. + * There is some handshake that takes place between us and the monitor + * to acquire the necessary keys. These are used to generate an + * 'authorizer' that we use when connecting to a service (mds, osd). + */ + +struct ceph_auth_client; +struct ceph_authorizer; + +struct ceph_auth_client_ops { + const char *name; + + /* + * true if we are authenticated and can connect to + * services. + */ + int (*is_authenticated)(struct ceph_auth_client *ac); + + /* + * true if we should (re)authenticate, e.g., when our tickets + * are getting old and crusty. + */ + int (*should_authenticate)(struct ceph_auth_client *ac); + + /* + * build requests and process replies during monitor + * handshake. if handle_reply returns -EAGAIN, we build + * another request. + */ + int (*build_request)(struct ceph_auth_client *ac, void *buf, void *end); + int (*handle_reply)(struct ceph_auth_client *ac, int result, + void *buf, void *end); + + /* + * Create authorizer for connecting to a service, and verify + * the response to authenticate the service. + */ + int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type, + struct ceph_authorizer **a, + void **buf, size_t *len, + void **reply_buf, size_t *reply_len); + int (*verify_authorizer_reply)(struct ceph_auth_client *ac, + struct ceph_authorizer *a, size_t len); + void (*destroy_authorizer)(struct ceph_auth_client *ac, + struct ceph_authorizer *a); + void (*invalidate_authorizer)(struct ceph_auth_client *ac, + int peer_type); + + /* reset when we (re)connect to a monitor */ + void (*reset)(struct ceph_auth_client *ac); + + void (*destroy)(struct ceph_auth_client *ac); +}; + +struct ceph_auth_client { + u32 protocol; /* CEPH_AUTH_* */ + void *private; /* for use by protocol implementation */ + const struct ceph_auth_client_ops *ops; /* null iff protocol==0 */ + + bool negotiating; /* true if negotiating protocol */ + const char *name; /* entity name */ + u64 global_id; /* our unique id in system */ + const char *secret; /* our secret key */ + unsigned want_keys; /* which services we want */ +}; + +extern struct ceph_auth_client *ceph_auth_init(const char *name, + const char *secret); +extern void ceph_auth_destroy(struct ceph_auth_client *ac); + +extern void ceph_auth_reset(struct ceph_auth_client *ac); + +extern int ceph_auth_build_hello(struct ceph_auth_client *ac, + void *buf, size_t len); +extern int ceph_handle_auth_reply(struct ceph_auth_client *ac, + void *buf, size_t len, + void *reply_buf, size_t reply_len); +extern int ceph_entity_name_encode(const char *name, void **p, void *end); + +extern int ceph_build_auth(struct ceph_auth_client *ac, + void *msg_buf, size_t msg_len); + +extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); + +#endif diff --git a/include/linux/ceph/buffer.h b/include/linux/ceph/buffer.h new file mode 100644 index 000000000000..58d19014068f --- /dev/null +++ b/include/linux/ceph/buffer.h @@ -0,0 +1,39 @@ +#ifndef __FS_CEPH_BUFFER_H +#define __FS_CEPH_BUFFER_H + +#include <linux/kref.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <linux/types.h> +#include <linux/uio.h> + +/* + * a simple reference counted buffer. + * + * use kmalloc for small sizes (<= one page), vmalloc for larger + * sizes. + */ +struct ceph_buffer { + struct kref kref; + struct kvec vec; + size_t alloc_len; + bool is_vmalloc; +}; + +extern struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp); +extern void ceph_buffer_release(struct kref *kref); + +static inline struct ceph_buffer *ceph_buffer_get(struct ceph_buffer *b) +{ + kref_get(&b->kref); + return b; +} + +static inline void ceph_buffer_put(struct ceph_buffer *b) +{ + kref_put(&b->kref, ceph_buffer_release); +} + +extern int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end); + +#endif diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h new file mode 100644 index 000000000000..aa2e19182d99 --- /dev/null +++ b/include/linux/ceph/ceph_debug.h @@ -0,0 +1,38 @@ +#ifndef _FS_CEPH_DEBUG_H +#define _FS_CEPH_DEBUG_H + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG + +/* + * wrap pr_debug to include a filename:lineno prefix on each line. + * this incurs some overhead (kernel size and execution time) due to + * the extra function call at each call site. + */ + +# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) +extern const char *ceph_file_part(const char *s, int len); +# define dout(fmt, ...) \ + pr_debug("%.*s %12.12s:%-4d : " fmt, \ + 8 - (int)sizeof(KBUILD_MODNAME), " ", \ + ceph_file_part(__FILE__, sizeof(__FILE__)), \ + __LINE__, ##__VA_ARGS__) +# else +/* faux printk call just to see any compiler warnings. */ +# define dout(fmt, ...) do { \ + if (0) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ + } while (0) +# endif + +#else + +/* + * or, just wrap pr_debug + */ +# define dout(fmt, ...) pr_debug(" " fmt, ##__VA_ARGS__) + +#endif + +#endif diff --git a/include/linux/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h new file mode 100644 index 000000000000..5babb8e95352 --- /dev/null +++ b/include/linux/ceph/ceph_frag.h @@ -0,0 +1,109 @@ +#ifndef FS_CEPH_FRAG_H +#define FS_CEPH_FRAG_H + +/* + * "Frags" are a way to describe a subset of a 32-bit number space, + * using a mask and a value to match against that mask. Any given frag + * (subset of the number space) can be partitioned into 2^n sub-frags. + * + * Frags are encoded into a 32-bit word: + * 8 upper bits = "bits" + * 24 lower bits = "value" + * (We could go to 5+27 bits, but who cares.) + * + * We use the _most_ significant bits of the 24 bit value. This makes + * values logically sort. + * + * Unfortunately, because the "bits" field is still in the high bits, we + * can't sort encoded frags numerically. However, it does allow you + * to feed encoded frags as values into frag_contains_value. + */ +static inline __u32 ceph_frag_make(__u32 b, __u32 v) +{ + return (b << 24) | + (v & (0xffffffu << (24-b)) & 0xffffffu); +} +static inline __u32 ceph_frag_bits(__u32 f) +{ + return f >> 24; +} +static inline __u32 ceph_frag_value(__u32 f) +{ + return f & 0xffffffu; +} +static inline __u32 ceph_frag_mask(__u32 f) +{ + return (0xffffffu << (24-ceph_frag_bits(f))) & 0xffffffu; +} +static inline __u32 ceph_frag_mask_shift(__u32 f) +{ + return 24 - ceph_frag_bits(f); +} + +static inline int ceph_frag_contains_value(__u32 f, __u32 v) +{ + return (v & ceph_frag_mask(f)) == ceph_frag_value(f); +} +static inline int ceph_frag_contains_frag(__u32 f, __u32 sub) +{ + /* is sub as specific as us, and contained by us? */ + return ceph_frag_bits(sub) >= ceph_frag_bits(f) && + (ceph_frag_value(sub) & ceph_frag_mask(f)) == ceph_frag_value(f); +} + +static inline __u32 ceph_frag_parent(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f) - 1, + ceph_frag_value(f) & (ceph_frag_mask(f) << 1)); +} +static inline int ceph_frag_is_left_child(__u32 f) +{ + return ceph_frag_bits(f) > 0 && + (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 0; +} +static inline int ceph_frag_is_right_child(__u32 f) +{ + return ceph_frag_bits(f) > 0 && + (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 1; +} +static inline __u32 ceph_frag_sibling(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f), + ceph_frag_value(f) ^ (0x1000000 >> ceph_frag_bits(f))); +} +static inline __u32 ceph_frag_left_child(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f)+1, ceph_frag_value(f)); +} +static inline __u32 ceph_frag_right_child(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f)+1, + ceph_frag_value(f) | (0x1000000 >> (1+ceph_frag_bits(f)))); +} +static inline __u32 ceph_frag_make_child(__u32 f, int by, int i) +{ + int newbits = ceph_frag_bits(f) + by; + return ceph_frag_make(newbits, + ceph_frag_value(f) | (i << (24 - newbits))); +} +static inline int ceph_frag_is_leftmost(__u32 f) +{ + return ceph_frag_value(f) == 0; +} +static inline int ceph_frag_is_rightmost(__u32 f) +{ + return ceph_frag_value(f) == ceph_frag_mask(f); +} +static inline __u32 ceph_frag_next(__u32 f) +{ + return ceph_frag_make(ceph_frag_bits(f), + ceph_frag_value(f) + (0x1000000 >> ceph_frag_bits(f))); +} + +/* + * comparator to sort frags logically, as when traversing the + * number space in ascending order... + */ +int ceph_frag_compare(__u32 a, __u32 b); + +#endif diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h new file mode 100644 index 000000000000..c3c74aef289d --- /dev/null +++ b/include/linux/ceph/ceph_fs.h @@ -0,0 +1,729 @@ +/* + * ceph_fs.h - Ceph constants and data types to share between kernel and + * user space. + * + * Most types in this file are defined as little-endian, and are + * primarily intended to describe data structures that pass over the + * wire or that are stored on disk. + * + * LGPL2 + */ + +#ifndef CEPH_FS_H +#define CEPH_FS_H + +#include "msgr.h" +#include "rados.h" + +/* + * subprotocol versions. when specific messages types or high-level + * protocols change, bump the affected components. we keep rev + * internal cluster protocols separately from the public, + * client-facing protocol. + */ +#define CEPH_OSD_PROTOCOL 8 /* cluster internal */ +#define CEPH_MDS_PROTOCOL 12 /* cluster internal */ +#define CEPH_MON_PROTOCOL 5 /* cluster internal */ +#define CEPH_OSDC_PROTOCOL 24 /* server/client */ +#define CEPH_MDSC_PROTOCOL 32 /* server/client */ +#define CEPH_MONC_PROTOCOL 15 /* server/client */ + + +#define CEPH_INO_ROOT 1 +#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ + +/* arbitrary limit on max # of monitors (cluster of 3 is typical) */ +#define CEPH_MAX_MON 31 + + +/* + * feature bits + */ +#define CEPH_FEATURE_UID (1<<0) +#define CEPH_FEATURE_NOSRCADDR (1<<1) +#define CEPH_FEATURE_MONCLOCKCHECK (1<<2) +#define CEPH_FEATURE_FLOCK (1<<3) + + +/* + * ceph_file_layout - describe data layout for a file/inode + */ +struct ceph_file_layout { + /* file -> object mapping */ + __le32 fl_stripe_unit; /* stripe unit, in bytes. must be multiple + of page size. */ + __le32 fl_stripe_count; /* over this many objects */ + __le32 fl_object_size; /* until objects are this big, then move to + new objects */ + __le32 fl_cas_hash; /* 0 = none; 1 = sha256 */ + + /* pg -> disk layout */ + __le32 fl_object_stripe_unit; /* for per-object parity, if any */ + + /* object -> pg layout */ + __le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */ + __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ +} __attribute__ ((packed)); + +#define CEPH_MIN_STRIPE_UNIT 65536 + +int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); + + +/* crypto algorithms */ +#define CEPH_CRYPTO_NONE 0x0 +#define CEPH_CRYPTO_AES 0x1 + +#define CEPH_AES_IV "cephsageyudagreg" + +/* security/authentication protocols */ +#define CEPH_AUTH_UNKNOWN 0x0 +#define CEPH_AUTH_NONE 0x1 +#define CEPH_AUTH_CEPHX 0x2 + +#define CEPH_AUTH_UID_DEFAULT ((__u64) -1) + + +/********************************************* + * message layer + */ + +/* + * message types + */ + +/* misc */ +#define CEPH_MSG_SHUTDOWN 1 +#define CEPH_MSG_PING 2 + +/* client <-> monitor */ +#define CEPH_MSG_MON_MAP 4 +#define CEPH_MSG_MON_GET_MAP 5 +#define CEPH_MSG_STATFS 13 +#define CEPH_MSG_STATFS_REPLY 14 +#define CEPH_MSG_MON_SUBSCRIBE 15 +#define CEPH_MSG_MON_SUBSCRIBE_ACK 16 +#define CEPH_MSG_AUTH 17 +#define CEPH_MSG_AUTH_REPLY 18 + +/* client <-> mds */ +#define CEPH_MSG_MDS_MAP 21 + +#define CEPH_MSG_CLIENT_SESSION 22 +#define CEPH_MSG_CLIENT_RECONNECT 23 + +#define CEPH_MSG_CLIENT_REQUEST 24 +#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25 +#define CEPH_MSG_CLIENT_REPLY 26 +#define CEPH_MSG_CLIENT_CAPS 0x310 +#define CEPH_MSG_CLIENT_LEASE 0x311 +#define CEPH_MSG_CLIENT_SNAP 0x312 +#define CEPH_MSG_CLIENT_CAPRELEASE 0x313 + +/* pool ops */ +#define CEPH_MSG_POOLOP_REPLY 48 +#define CEPH_MSG_POOLOP 49 + + +/* osd */ +#define CEPH_MSG_OSD_MAP 41 +#define CEPH_MSG_OSD_OP 42 +#define CEPH_MSG_OSD_OPREPLY 43 + +/* pool operations */ +enum { + POOL_OP_CREATE = 0x01, + POOL_OP_DELETE = 0x02, + POOL_OP_AUID_CHANGE = 0x03, + POOL_OP_CREATE_SNAP = 0x11, + POOL_OP_DELETE_SNAP = 0x12, + POOL_OP_CREATE_UNMANAGED_SNAP = 0x21, + POOL_OP_DELETE_UNMANAGED_SNAP = 0x22, +}; + +struct ceph_mon_request_header { + __le64 have_version; + __le16 session_mon; + __le64 session_mon_tid; +} __attribute__ ((packed)); + +struct ceph_mon_statfs { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; +} __attribute__ ((packed)); + +struct ceph_statfs { + __le64 kb, kb_used, kb_avail; + __le64 num_objects; +} __attribute__ ((packed)); + +struct ceph_mon_statfs_reply { + struct ceph_fsid fsid; + __le64 version; + struct ceph_statfs st; +} __attribute__ ((packed)); + +const char *ceph_pool_op_name(int op); + +struct ceph_mon_poolop { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; + __le32 pool; + __le32 op; + __le64 auid; + __le64 snapid; + __le32 name_len; +} __attribute__ ((packed)); + +struct ceph_mon_poolop_reply { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; + __le32 reply_code; + __le32 epoch; + char has_data; + char data[0]; +} __attribute__ ((packed)); + +struct ceph_mon_unmanaged_snap { + __le64 snapid; +} __attribute__ ((packed)); + +struct ceph_osd_getmap { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; + __le32 start; +} __attribute__ ((packed)); + +struct ceph_mds_getmap { + struct ceph_mon_request_header monhdr; + struct ceph_fsid fsid; +} __attribute__ ((packed)); + +struct ceph_client_mount { + struct ceph_mon_request_header monhdr; +} __attribute__ ((packed)); + +struct ceph_mon_subscribe_item { + __le64 have_version; __le64 have; + __u8 onetime; +} __attribute__ ((packed)); + +struct ceph_mon_subscribe_ack { + __le32 duration; /* seconds */ + struct ceph_fsid fsid; +} __attribute__ ((packed)); + +/* + * mds states + * > 0 -> in + * <= 0 -> out + */ +#define CEPH_MDS_STATE_DNE 0 /* down, does not exist. */ +#define CEPH_MDS_STATE_STOPPED -1 /* down, once existed, but no subtrees. + empty log. */ +#define CEPH_MDS_STATE_BOOT -4 /* up, boot announcement. */ +#define CEPH_MDS_STATE_STANDBY -5 /* up, idle. waiting for assignment. */ +#define CEPH_MDS_STATE_CREATING -6 /* up, creating MDS instance. */ +#define CEPH_MDS_STATE_STARTING -7 /* up, starting previously stopped mds */ +#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */ + +#define CEPH_MDS_STATE_REPLAY 8 /* up, replaying journal. */ +#define CEPH_MDS_STATE_RESOLVE 9 /* up, disambiguating distributed + operations (import, rename, etc.) */ +#define CEPH_MDS_STATE_RECONNECT 10 /* up, reconnect to clients */ +#define CEPH_MDS_STATE_REJOIN 11 /* up, rejoining distributed cache */ +#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */ +#define CEPH_MDS_STATE_ACTIVE 13 /* up, active */ +#define CEPH_MDS_STATE_STOPPING 14 /* up, but exporting metadata */ + +extern const char *ceph_mds_state_name(int s); + + +/* + * metadata lock types. + * - these are bitmasks.. we can compose them + * - they also define the lock ordering by the MDS + * - a few of these are internal to the mds + */ +#define CEPH_LOCK_DVERSION 1 +#define CEPH_LOCK_DN 2 +#define CEPH_LOCK_ISNAP 16 +#define CEPH_LOCK_IVERSION 32 /* mds internal */ +#define CEPH_LOCK_IFILE 64 +#define CEPH_LOCK_IAUTH 128 +#define CEPH_LOCK_ILINK 256 +#define CEPH_LOCK_IDFT 512 /* dir frag tree */ +#define CEPH_LOCK_INEST 1024 /* mds internal */ +#define CEPH_LOCK_IXATTR 2048 +#define CEPH_LOCK_IFLOCK 4096 /* advisory file locks */ +#define CEPH_LOCK_INO 8192 /* immutable inode bits; not a lock */ + +/* client_session ops */ +enum { + CEPH_SESSION_REQUEST_OPEN, + CEPH_SESSION_OPEN, + CEPH_SESSION_REQUEST_CLOSE, + CEPH_SESSION_CLOSE, + CEPH_SESSION_REQUEST_RENEWCAPS, + CEPH_SESSION_RENEWCAPS, + CEPH_SESSION_STALE, + CEPH_SESSION_RECALL_STATE, +}; + +extern const char *ceph_session_op_name(int op); + +struct ceph_mds_session_head { + __le32 op; + __le64 seq; + struct ceph_timespec stamp; + __le32 max_caps, max_leases; +} __attribute__ ((packed)); + +/* client_request */ +/* + * metadata ops. + * & 0x001000 -> write op + * & 0x010000 -> follow symlink (e.g. stat(), not lstat()). + & & 0x100000 -> use weird ino/path trace + */ +#define CEPH_MDS_OP_WRITE 0x001000 +enum { + CEPH_MDS_OP_LOOKUP = 0x00100, + CEPH_MDS_OP_GETATTR = 0x00101, + CEPH_MDS_OP_LOOKUPHASH = 0x00102, + CEPH_MDS_OP_LOOKUPPARENT = 0x00103, + + CEPH_MDS_OP_SETXATTR = 0x01105, + CEPH_MDS_OP_RMXATTR = 0x01106, + CEPH_MDS_OP_SETLAYOUT = 0x01107, + CEPH_MDS_OP_SETATTR = 0x01108, + CEPH_MDS_OP_SETFILELOCK= 0x01109, + CEPH_MDS_OP_GETFILELOCK= 0x00110, + CEPH_MDS_OP_SETDIRLAYOUT=0x0110a, + + CEPH_MDS_OP_MKNOD = 0x01201, + CEPH_MDS_OP_LINK = 0x01202, + CEPH_MDS_OP_UNLINK = 0x01203, + CEPH_MDS_OP_RENAME = 0x01204, + CEPH_MDS_OP_MKDIR = 0x01220, + CEPH_MDS_OP_RMDIR = 0x01221, + CEPH_MDS_OP_SYMLINK = 0x01222, + + CEPH_MDS_OP_CREATE = 0x01301, + CEPH_MDS_OP_OPEN = 0x00302, + CEPH_MDS_OP_READDIR = 0x00305, + + CEPH_MDS_OP_LOOKUPSNAP = 0x00400, + CEPH_MDS_OP_MKSNAP = 0x01400, + CEPH_MDS_OP_RMSNAP = 0x01401, + CEPH_MDS_OP_LSSNAP = 0x00402, +}; + +extern const char *ceph_mds_op_name(int op); + + +#define CEPH_SETATTR_MODE 1 +#define CEPH_SETATTR_UID 2 +#define CEPH_SETATTR_GID 4 +#define CEPH_SETATTR_MTIME 8 +#define CEPH_SETATTR_ATIME 16 +#define CEPH_SETATTR_SIZE 32 +#define CEPH_SETATTR_CTIME 64 + +union ceph_mds_request_args { + struct { + __le32 mask; /* CEPH_CAP_* */ + } __attribute__ ((packed)) getattr; + struct { + __le32 mode; + __le32 uid; + __le32 gid; + struct ceph_timespec mtime; + struct ceph_timespec atime; + __le64 size, old_size; /* old_size needed by truncate */ + __le32 mask; /* CEPH_SETATTR_* */ + } __attribute__ ((packed)) setattr; + struct { + __le32 frag; /* which dir fragment */ + __le32 max_entries; /* how many dentries to grab */ + __le32 max_bytes; + } __attribute__ ((packed)) readdir; + struct { + __le32 mode; + __le32 rdev; + } __attribute__ ((packed)) mknod; + struct { + __le32 mode; + } __attribute__ ((packed)) mkdir; + struct { + __le32 flags; + __le32 mode; + __le32 stripe_unit; /* layout for newly created file */ + __le32 stripe_count; /* ... */ + __le32 object_size; + __le32 file_replication; + __le32 preferred; + } __attribute__ ((packed)) open; + struct { + __le32 flags; + } __attribute__ ((packed)) setxattr; + struct { + struct ceph_file_layout layout; + } __attribute__ ((packed)) setlayout; + struct { + __u8 rule; /* currently fcntl or flock */ + __u8 type; /* shared, exclusive, remove*/ + __le64 pid; /* process id requesting the lock */ + __le64 pid_namespace; + __le64 start; /* initial location to lock */ + __le64 length; /* num bytes to lock from start */ + __u8 wait; /* will caller wait for lock to become available? */ + } __attribute__ ((packed)) filelock_change; +} __attribute__ ((packed)); + +#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */ +#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */ + +struct ceph_mds_request_head { + __le64 oldest_client_tid; + __le32 mdsmap_epoch; /* on client */ + __le32 flags; /* CEPH_MDS_FLAG_* */ + __u8 num_retry, num_fwd; /* count retry, fwd attempts */ + __le16 num_releases; /* # include cap/lease release records */ + __le32 op; /* mds op code */ + __le32 caller_uid, caller_gid; + __le64 ino; /* use this ino for openc, mkdir, mknod, + etc. (if replaying) */ + union ceph_mds_request_args args; +} __attribute__ ((packed)); + +/* cap/lease release record */ +struct ceph_mds_request_release { + __le64 ino, cap_id; /* ino and unique cap id */ + __le32 caps, wanted; /* new issued, wanted */ + __le32 seq, issue_seq, mseq; + __le32 dname_seq; /* if releasing a dentry lease, a */ + __le32 dname_len; /* string follows. */ +} __attribute__ ((packed)); + +/* client reply */ +struct ceph_mds_reply_head { + __le32 op; + __le32 result; + __le32 mdsmap_epoch; + __u8 safe; /* true if committed to disk */ + __u8 is_dentry, is_target; /* true if dentry, target inode records + are included with reply */ +} __attribute__ ((packed)); + +/* one for each node split */ +struct ceph_frag_tree_split { + __le32 frag; /* this frag splits... */ + __le32 by; /* ...by this many bits */ +} __attribute__ ((packed)); + +struct ceph_frag_tree_head { + __le32 nsplits; /* num ceph_frag_tree_split records */ + struct ceph_frag_tree_split splits[]; +} __attribute__ ((packed)); + +/* capability issue, for bundling with mds reply */ +struct ceph_mds_reply_cap { + __le32 caps, wanted; /* caps issued, wanted */ + __le64 cap_id; + __le32 seq, mseq; + __le64 realm; /* snap realm */ + __u8 flags; /* CEPH_CAP_FLAG_* */ +} __attribute__ ((packed)); + +#define CEPH_CAP_FLAG_AUTH 1 /* cap is issued by auth mds */ + +/* inode record, for bundling with mds reply */ +struct ceph_mds_reply_inode { + __le64 ino; + __le64 snapid; + __le32 rdev; + __le64 version; /* inode version */ + __le64 xattr_version; /* version for xattr blob */ + struct ceph_mds_reply_cap cap; /* caps issued for this inode */ + struct ceph_file_layout layout; + struct ceph_timespec ctime, mtime, atime; + __le32 time_warp_seq; + __le64 size, max_size, truncate_size; + __le32 truncate_seq; + __le32 mode, uid, gid; + __le32 nlink; + __le64 files, subdirs, rbytes, rfiles, rsubdirs; /* dir stats */ + struct ceph_timespec rctime; + struct ceph_frag_tree_head fragtree; /* (must be at end of struct) */ +} __attribute__ ((packed)); +/* followed by frag array, then symlink string, then xattr blob */ + +/* reply_lease follows dname, and reply_inode */ +struct ceph_mds_reply_lease { + __le16 mask; /* lease type(s) */ + __le32 duration_ms; /* lease duration */ + __le32 seq; +} __attribute__ ((packed)); + +struct ceph_mds_reply_dirfrag { + __le32 frag; /* fragment */ + __le32 auth; /* auth mds, if this is a delegation point */ + __le32 ndist; /* number of mds' this is replicated on */ + __le32 dist[]; +} __attribute__ ((packed)); + +#define CEPH_LOCK_FCNTL 1 +#define CEPH_LOCK_FLOCK 2 + +#define CEPH_LOCK_SHARED 1 +#define CEPH_LOCK_EXCL 2 +#define CEPH_LOCK_UNLOCK 4 + +struct ceph_filelock { + __le64 start;/* file offset to start lock at */ + __le64 length; /* num bytes to lock; 0 for all following start */ + __le64 client; /* which client holds the lock */ + __le64 pid; /* process id holding the lock on the client */ + __le64 pid_namespace; + __u8 type; /* shared lock, exclusive lock, or unlock */ +} __attribute__ ((packed)); + + +/* file access modes */ +#define CEPH_FILE_MODE_PIN 0 +#define CEPH_FILE_MODE_RD 1 +#define CEPH_FILE_MODE_WR 2 +#define CEPH_FILE_MODE_RDWR 3 /* RD | WR */ +#define CEPH_FILE_MODE_LAZY 4 /* lazy io */ +#define CEPH_FILE_MODE_NUM 8 /* bc these are bit fields.. mostly */ + +int ceph_flags_to_mode(int flags); + + +/* capability bits */ +#define CEPH_CAP_PIN 1 /* no specific capabilities beyond the pin */ + +/* generic cap bits */ +#define CEPH_CAP_GSHARED 1 /* client can reads */ +#define CEPH_CAP_GEXCL 2 /* client can read and update */ +#define CEPH_CAP_GCACHE 4 /* (file) client can cache reads */ +#define CEPH_CAP_GRD 8 /* (file) client can read */ +#define CEPH_CAP_GWR 16 /* (file) client can write */ +#define CEPH_CAP_GBUFFER 32 /* (file) client can buffer writes */ +#define CEPH_CAP_GWREXTEND 64 /* (file) client can extend EOF */ +#define CEPH_CAP_GLAZYIO 128 /* (file) client can perform lazy io */ + +/* per-lock shift */ +#define CEPH_CAP_SAUTH 2 +#define CEPH_CAP_SLINK 4 +#define CEPH_CAP_SXATTR 6 +#define CEPH_CAP_SFILE 8 +#define CEPH_CAP_SFLOCK 20 + +#define CEPH_CAP_BITS 22 + +/* composed values */ +#define CEPH_CAP_AUTH_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SAUTH) +#define CEPH_CAP_AUTH_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SAUTH) +#define CEPH_CAP_LINK_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SLINK) +#define CEPH_CAP_LINK_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SLINK) +#define CEPH_CAP_XATTR_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SXATTR) +#define CEPH_CAP_XATTR_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SXATTR) +#define CEPH_CAP_FILE(x) (x << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_CACHE (CEPH_CAP_GCACHE << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_RD (CEPH_CAP_GRD << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_WR (CEPH_CAP_GWR << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_BUFFER (CEPH_CAP_GBUFFER << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_WREXTEND (CEPH_CAP_GWREXTEND << CEPH_CAP_SFILE) +#define CEPH_CAP_FILE_LAZYIO (CEPH_CAP_GLAZYIO << CEPH_CAP_SFILE) +#define CEPH_CAP_FLOCK_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SFLOCK) +#define CEPH_CAP_FLOCK_EXCL (CEPH_CAP_GEXCL << CEPH_CAP_SFLOCK) + + +/* cap masks (for getattr) */ +#define CEPH_STAT_CAP_INODE CEPH_CAP_PIN +#define CEPH_STAT_CAP_TYPE CEPH_CAP_PIN /* mode >> 12 */ +#define CEPH_STAT_CAP_SYMLINK CEPH_CAP_PIN +#define CEPH_STAT_CAP_UID CEPH_CAP_AUTH_SHARED +#define CEPH_STAT_CAP_GID CEPH_CAP_AUTH_SHARED +#define CEPH_STAT_CAP_MODE CEPH_CAP_AUTH_SHARED +#define CEPH_STAT_CAP_NLINK CEPH_CAP_LINK_SHARED +#define CEPH_STAT_CAP_LAYOUT CEPH_CAP_FILE_SHARED +#define CEPH_STAT_CAP_MTIME CEPH_CAP_FILE_SHARED +#define CEPH_STAT_CAP_SIZE CEPH_CAP_FILE_SHARED +#define CEPH_STAT_CAP_ATIME CEPH_CAP_FILE_SHARED /* fixme */ +#define CEPH_STAT_CAP_XATTR CEPH_CAP_XATTR_SHARED +#define CEPH_STAT_CAP_INODE_ALL (CEPH_CAP_PIN | \ + CEPH_CAP_AUTH_SHARED | \ + CEPH_CAP_LINK_SHARED | \ + CEPH_CAP_FILE_SHARED | \ + CEPH_CAP_XATTR_SHARED) + +#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED | \ + CEPH_CAP_LINK_SHARED | \ + CEPH_CAP_XATTR_SHARED | \ + CEPH_CAP_FILE_SHARED) +#define CEPH_CAP_ANY_RD (CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_RD | \ + CEPH_CAP_FILE_CACHE) + +#define CEPH_CAP_ANY_EXCL (CEPH_CAP_AUTH_EXCL | \ + CEPH_CAP_LINK_EXCL | \ + CEPH_CAP_XATTR_EXCL | \ + CEPH_CAP_FILE_EXCL) +#define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER | \ + CEPH_CAP_FILE_EXCL) +#define CEPH_CAP_ANY_WR (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR) +#define CEPH_CAP_ANY (CEPH_CAP_ANY_RD | CEPH_CAP_ANY_EXCL | \ + CEPH_CAP_ANY_FILE_WR | CEPH_CAP_FILE_LAZYIO | \ + CEPH_CAP_PIN) + +#define CEPH_CAP_LOCKS (CEPH_LOCK_IFILE | CEPH_LOCK_IAUTH | CEPH_LOCK_ILINK | \ + CEPH_LOCK_IXATTR) + +int ceph_caps_for_mode(int mode); + +enum { + CEPH_CAP_OP_GRANT, /* mds->client grant */ + CEPH_CAP_OP_REVOKE, /* mds->client revoke */ + CEPH_CAP_OP_TRUNC, /* mds->client trunc notify */ + CEPH_CAP_OP_EXPORT, /* mds has exported the cap */ + CEPH_CAP_OP_IMPORT, /* mds has imported the cap */ + CEPH_CAP_OP_UPDATE, /* client->mds update */ + CEPH_CAP_OP_DROP, /* client->mds drop cap bits */ + CEPH_CAP_OP_FLUSH, /* client->mds cap writeback */ + CEPH_CAP_OP_FLUSH_ACK, /* mds->client flushed */ + CEPH_CAP_OP_FLUSHSNAP, /* client->mds flush snapped metadata */ + CEPH_CAP_OP_FLUSHSNAP_ACK, /* mds->client flushed snapped metadata */ + CEPH_CAP_OP_RELEASE, /* client->mds release (clean) cap */ + CEPH_CAP_OP_RENEW, /* client->mds renewal request */ +}; + +extern const char *ceph_cap_op_name(int op); + +/* + * caps message, used for capability callbacks, acks, requests, etc. + */ +struct ceph_mds_caps { + __le32 op; /* CEPH_CAP_OP_* */ + __le64 ino, realm; + __le64 cap_id; + __le32 seq, issue_seq; + __le32 caps, wanted, dirty; /* latest issued/wanted/dirty */ + __le32 migrate_seq; + __le64 snap_follows; + __le32 snap_trace_len; + + /* authlock */ + __le32 uid, gid, mode; + + /* linklock */ + __le32 nlink; + + /* xattrlock */ + __le32 xattr_len; + __le64 xattr_version; + + /* filelock */ + __le64 size, max_size, truncate_size; + __le32 truncate_seq; + struct ceph_timespec mtime, atime, ctime; + struct ceph_file_layout layout; + __le32 time_warp_seq; +} __attribute__ ((packed)); + +/* cap release msg head */ +struct ceph_mds_cap_release { + __le32 num; /* number of cap_items that follow */ +} __attribute__ ((packed)); + +struct ceph_mds_cap_item { + __le64 ino; + __le64 cap_id; + __le32 migrate_seq, seq; +} __attribute__ ((packed)); + +#define CEPH_MDS_LEASE_REVOKE 1 /* mds -> client */ +#define CEPH_MDS_LEASE_RELEASE 2 /* client -> mds */ +#define CEPH_MDS_LEASE_RENEW 3 /* client <-> mds */ +#define CEPH_MDS_LEASE_REVOKE_ACK 4 /* client -> mds */ + +extern const char *ceph_lease_op_name(int o); + +/* lease msg header */ +struct ceph_mds_lease { + __u8 action; /* CEPH_MDS_LEASE_* */ + __le16 mask; /* which lease */ + __le64 ino; + __le64 first, last; /* snap range */ + __le32 seq; + __le32 duration_ms; /* duration of renewal */ +} __attribute__ ((packed)); +/* followed by a __le32+string for dname */ + +/* client reconnect */ +struct ceph_mds_cap_reconnect { + __le64 cap_id; + __le32 wanted; + __le32 issued; + __le64 snaprealm; + __le64 pathbase; /* base ino for our path to this ino */ + __le32 flock_len; /* size of flock state blob, if any */ +} __attribute__ ((packed)); +/* followed by flock blob */ + +struct ceph_mds_cap_reconnect_v1 { + __le64 cap_id; + __le32 wanted; + __le32 issued; + __le64 size; + struct ceph_timespec mtime, atime; + __le64 snaprealm; + __le64 pathbase; /* base ino for our path to this ino */ +} __attribute__ ((packed)); + +struct ceph_mds_snaprealm_reconnect { + __le64 ino; /* snap realm base */ + __le64 seq; /* snap seq for this snap realm */ + __le64 parent; /* parent realm */ +} __attribute__ ((packed)); + +/* + * snaps + */ +enum { + CEPH_SNAP_OP_UPDATE, /* CREATE or DESTROY */ + CEPH_SNAP_OP_CREATE, + CEPH_SNAP_OP_DESTROY, + CEPH_SNAP_OP_SPLIT, +}; + +extern const char *ceph_snap_op_name(int o); + +/* snap msg header */ +struct ceph_mds_snap_head { + __le32 op; /* CEPH_SNAP_OP_* */ + __le64 split; /* ino to split off, if any */ + __le32 num_split_inos; /* # inos belonging to new child realm */ + __le32 num_split_realms; /* # child realms udner new child realm */ + __le32 trace_len; /* size of snap trace blob */ +} __attribute__ ((packed)); +/* followed by split ino list, then split realms, then the trace blob */ + +/* + * encode info about a snaprealm, as viewed by a client + */ +struct ceph_mds_snap_realm { + __le64 ino; /* ino */ + __le64 created; /* snap: when created */ + __le64 parent; /* ino: parent realm */ + __le64 parent_since; /* snap: same parent since */ + __le64 seq; /* snap: version */ + __le32 num_snaps; + __le32 num_prior_parent_snaps; +} __attribute__ ((packed)); +/* followed by my snap list, then prior parent snap list */ + +#endif diff --git a/include/linux/ceph/ceph_hash.h b/include/linux/ceph/ceph_hash.h new file mode 100644 index 000000000000..d099c3f90236 --- /dev/null +++ b/include/linux/ceph/ceph_hash.h @@ -0,0 +1,13 @@ +#ifndef FS_CEPH_HASH_H +#define FS_CEPH_HASH_H + +#define CEPH_STR_HASH_LINUX 0x1 /* linux dcache hash */ +#define CEPH_STR_HASH_RJENKINS 0x2 /* robert jenkins' */ + +extern unsigned ceph_str_hash_linux(const char *s, unsigned len); +extern unsigned ceph_str_hash_rjenkins(const char *s, unsigned len); + +extern unsigned ceph_str_hash(int type, const char *s, unsigned len); +extern const char *ceph_str_hash_name(int type); + +#endif diff --git a/include/linux/ceph/debugfs.h b/include/linux/ceph/debugfs.h new file mode 100644 index 000000000000..2a79702e092b --- /dev/null +++ b/include/linux/ceph/debugfs.h @@ -0,0 +1,33 @@ +#ifndef _FS_CEPH_DEBUGFS_H +#define _FS_CEPH_DEBUGFS_H + +#include "ceph_debug.h" +#include "types.h" + +#define CEPH_DEFINE_SHOW_FUNC(name) \ +static int name##_open(struct inode *inode, struct file *file) \ +{ \ + struct seq_file *sf; \ + int ret; \ + \ + ret = single_open(file, name, NULL); \ + sf = file->private_data; \ + sf->private = inode->i_private; \ + return ret; \ +} \ + \ +static const struct file_operations name##_fops = { \ + .open = name##_open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +}; + +/* debugfs.c */ +extern int ceph_debugfs_init(void); +extern void ceph_debugfs_cleanup(void); +extern int ceph_debugfs_client_init(struct ceph_client *client); +extern void ceph_debugfs_client_cleanup(struct ceph_client *client); + +#endif + diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h new file mode 100644 index 000000000000..c5b6939fb32a --- /dev/null +++ b/include/linux/ceph/decode.h @@ -0,0 +1,201 @@ +#ifndef __CEPH_DECODE_H +#define __CEPH_DECODE_H + +#include <asm/unaligned.h> +#include <linux/time.h> + +#include "types.h" + +/* + * in all cases, + * void **p pointer to position pointer + * void *end pointer to end of buffer (last byte + 1) + */ + +static inline u64 ceph_decode_64(void **p) +{ + u64 v = get_unaligned_le64(*p); + *p += sizeof(u64); + return v; +} +static inline u32 ceph_decode_32(void **p) +{ + u32 v = get_unaligned_le32(*p); + *p += sizeof(u32); + return v; +} +static inline u16 ceph_decode_16(void **p) +{ + u16 v = get_unaligned_le16(*p); + *p += sizeof(u16); + return v; +} +static inline u8 ceph_decode_8(void **p) +{ + u8 v = *(u8 *)*p; + (*p)++; + return v; +} +static inline void ceph_decode_copy(void **p, void *pv, size_t n) +{ + memcpy(pv, *p, n); + *p += n; +} + +/* + * bounds check input. + */ +#define ceph_decode_need(p, end, n, bad) \ + do { \ + if (unlikely(*(p) + (n) > (end))) \ + goto bad; \ + } while (0) + +#define ceph_decode_64_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u64), bad); \ + v = ceph_decode_64(p); \ + } while (0) +#define ceph_decode_32_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u32), bad); \ + v = ceph_decode_32(p); \ + } while (0) +#define ceph_decode_16_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u16), bad); \ + v = ceph_decode_16(p); \ + } while (0) +#define ceph_decode_8_safe(p, end, v, bad) \ + do { \ + ceph_decode_need(p, end, sizeof(u8), bad); \ + v = ceph_decode_8(p); \ + } while (0) + +#define ceph_decode_copy_safe(p, end, pv, n, bad) \ + do { \ + ceph_decode_need(p, end, n, bad); \ + ceph_decode_copy(p, pv, n); \ + } while (0) + +/* + * struct ceph_timespec <-> struct timespec + */ +static inline void ceph_decode_timespec(struct timespec *ts, + const struct ceph_timespec *tv) +{ + ts->tv_sec = le32_to_cpu(tv->tv_sec); + ts->tv_nsec = le32_to_cpu(tv->tv_nsec); +} +static inline void ceph_encode_timespec(struct ceph_timespec *tv, + const struct timespec *ts) +{ + tv->tv_sec = cpu_to_le32(ts->tv_sec); + tv->tv_nsec = cpu_to_le32(ts->tv_nsec); +} + +/* + * sockaddr_storage <-> ceph_sockaddr + */ +static inline void ceph_encode_addr(struct ceph_entity_addr *a) +{ + __be16 ss_family = htons(a->in_addr.ss_family); + a->in_addr.ss_family = *(__u16 *)&ss_family; +} +static inline void ceph_decode_addr(struct ceph_entity_addr *a) +{ + __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; + a->in_addr.ss_family = ntohs(ss_family); + WARN_ON(a->in_addr.ss_family == 512); +} + +/* + * encoders + */ +static inline void ceph_encode_64(void **p, u64 v) +{ + put_unaligned_le64(v, (__le64 *)*p); + *p += sizeof(u64); +} +static inline void ceph_encode_32(void **p, u32 v) +{ + put_unaligned_le32(v, (__le32 *)*p); + *p += sizeof(u32); +} +static inline void ceph_encode_16(void **p, u16 v) +{ + put_unaligned_le16(v, (__le16 *)*p); + *p += sizeof(u16); +} +static inline void ceph_encode_8(void **p, u8 v) +{ + *(u8 *)*p = v; + (*p)++; +} +static inline void ceph_encode_copy(void **p, const void *s, int len) +{ + memcpy(*p, s, len); + *p += len; +} + +/* + * filepath, string encoders + */ +static inline void ceph_encode_filepath(void **p, void *end, + u64 ino, const char *path) +{ + u32 len = path ? strlen(path) : 0; + BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end); + ceph_encode_8(p, 1); + ceph_encode_64(p, ino); + ceph_encode_32(p, len); + if (len) + memcpy(*p, path, len); + *p += len; +} + +static inline void ceph_encode_string(void **p, void *end, + const char *s, u32 len) +{ + BUG_ON(*p + sizeof(len) + len > end); + ceph_encode_32(p, len); + if (len) + memcpy(*p, s, len); + *p += len; +} + +#define ceph_encode_need(p, end, n, bad) \ + do { \ + if (unlikely(*(p) + (n) > (end))) \ + goto bad; \ + } while (0) + +#define ceph_encode_64_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u64), bad); \ + ceph_encode_64(p, v); \ + } while (0) +#define ceph_encode_32_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u32), bad); \ + ceph_encode_32(p, v); \ + } while (0) +#define ceph_encode_16_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u16), bad); \ + ceph_encode_16(p, v); \ + } while (0) + +#define ceph_encode_copy_safe(p, end, pv, n, bad) \ + do { \ + ceph_encode_need(p, end, n, bad); \ + ceph_encode_copy(p, pv, n); \ + } while (0) +#define ceph_encode_string_safe(p, end, s, n, bad) \ + do { \ + ceph_encode_need(p, end, n, bad); \ + ceph_encode_string(p, end, s, n); \ + } while (0) + + +#endif diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h new file mode 100644 index 000000000000..f22b2e941686 --- /dev/null +++ b/include/linux/ceph/libceph.h @@ -0,0 +1,249 @@ +#ifndef _FS_CEPH_LIBCEPH_H +#define _FS_CEPH_LIBCEPH_H + +#include "ceph_debug.h" + +#include <asm/unaligned.h> +#include <linux/backing-dev.h> +#include <linux/completion.h> +#include <linux/exportfs.h> +#include <linux/fs.h> +#include <linux/mempool.h> +#include <linux/pagemap.h> +#include <linux/wait.h> +#include <linux/writeback.h> +#include <linux/slab.h> + +#include "types.h" +#include "messenger.h" +#include "msgpool.h" +#include "mon_client.h" +#include "osd_client.h" +#include "ceph_fs.h" + +/* + * Supported features + */ +#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR +#define CEPH_FEATURE_REQUIRED_DEFAULT CEPH_FEATURE_NOSRCADDR + +/* + * mount options + */ +#define CEPH_OPT_FSID (1<<0) +#define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ +#define CEPH_OPT_MYIP (1<<2) /* specified my ip */ +#define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ + +#define CEPH_OPT_DEFAULT (0); + +#define ceph_set_opt(client, opt) \ + (client)->options->flags |= CEPH_OPT_##opt; +#define ceph_test_opt(client, opt) \ + (!!((client)->options->flags & CEPH_OPT_##opt)) + +struct ceph_options { + int flags; + struct ceph_fsid fsid; + struct ceph_entity_addr my_addr; + int mount_timeout; + int osd_idle_ttl; + int osd_timeout; + int osd_keepalive_timeout; + + /* + * any type that can't be simply compared or doesn't need need + * to be compared should go beyond this point, + * ceph_compare_options() should be updated accordingly + */ + + struct ceph_entity_addr *mon_addr; /* should be the first + pointer type of args */ + int num_mon; + char *name; + char *secret; +}; + +/* + * defaults + */ +#define CEPH_MOUNT_TIMEOUT_DEFAULT 60 +#define CEPH_OSD_TIMEOUT_DEFAULT 60 /* seconds */ +#define CEPH_OSD_KEEPALIVE_DEFAULT 5 +#define CEPH_OSD_IDLE_TTL_DEFAULT 60 +#define CEPH_MOUNT_RSIZE_DEFAULT (512*1024) /* readahead */ + +#define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) +#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +#define CEPH_AUTH_NAME_DEFAULT "guest" + +/* + * Delay telling the MDS we no longer want caps, in case we reopen + * the file. Delay a minimum amount of time, even if we send a cap + * message for some other reason. Otherwise, take the oppotunity to + * update the mds to avoid sending another message later. + */ +#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ +#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ + +#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4) + +/* mount state */ +enum { + CEPH_MOUNT_MOUNTING, + CEPH_MOUNT_MOUNTED, + CEPH_MOUNT_UNMOUNTING, + CEPH_MOUNT_UNMOUNTED, + CEPH_MOUNT_SHUTDOWN, +}; + +/* + * subtract jiffies + */ +static inline unsigned long time_sub(unsigned long a, unsigned long b) +{ + BUG_ON(time_after(b, a)); + return (long)a - (long)b; +} + +struct ceph_mds_client; + +/* + * per client state + * + * possibly shared by multiple mount points, if they are + * mounting the same ceph filesystem/cluster. + */ +struct ceph_client { + struct ceph_fsid fsid; + bool have_fsid; + + void *private; + + struct ceph_options *options; + + struct mutex mount_mutex; /* serialize mount attempts */ + wait_queue_head_t auth_wq; + int auth_err; + + int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *); + + u32 supported_features; + u32 required_features; + + struct ceph_messenger *msgr; /* messenger instance */ + struct ceph_mon_client monc; + struct ceph_osd_client osdc; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_dir; + struct dentry *debugfs_monmap; + struct dentry *debugfs_osdmap; +#endif +}; + + + +/* + * snapshots + */ + +/* + * A "snap context" is the set of existing snapshots when we + * write data. It is used by the OSD to guide its COW behavior. + * + * The ceph_snap_context is refcounted, and attached to each dirty + * page, indicating which context the dirty data belonged when it was + * dirtied. + */ +struct ceph_snap_context { + atomic_t nref; + u64 seq; + int num_snaps; + u64 snaps[]; +}; + +static inline struct ceph_snap_context * +ceph_get_snap_context(struct ceph_snap_context *sc) +{ + /* + printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), + atomic_read(&sc->nref)+1); + */ + if (sc) + atomic_inc(&sc->nref); + return sc; +} + +static inline void ceph_put_snap_context(struct ceph_snap_context *sc) +{ + if (!sc) + return; + /* + printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), + atomic_read(&sc->nref)-1); + */ + if (atomic_dec_and_test(&sc->nref)) { + /*printk(" deleting snap_context %p\n", sc);*/ + kfree(sc); + } +} + +/* + * calculate the number of pages a given length and offset map onto, + * if we align the data. + */ +static inline int calc_pages_for(u64 off, u64 len) +{ + return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) - + (off >> PAGE_CACHE_SHIFT); +} + +/* ceph_common.c */ +extern const char *ceph_msg_type_name(int type); +extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); +extern struct kmem_cache *ceph_inode_cachep; +extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_dentry_cachep; +extern struct kmem_cache *ceph_file_cachep; + +extern int ceph_parse_options(struct ceph_options **popt, char *options, + const char *dev_name, const char *dev_name_end, + int (*parse_extra_token)(char *c, void *private), + void *private); +extern void ceph_destroy_options(struct ceph_options *opt); +extern int ceph_compare_options(struct ceph_options *new_opt, + struct ceph_client *client); +extern struct ceph_client *ceph_create_client(struct ceph_options *opt, + void *private); +extern u64 ceph_client_id(struct ceph_client *client); +extern void ceph_destroy_client(struct ceph_client *client); +extern int __ceph_open_session(struct ceph_client *client, + unsigned long started); +extern int ceph_open_session(struct ceph_client *client); + +/* pagevec.c */ +extern void ceph_release_page_vector(struct page **pages, int num_pages); + +extern struct page **ceph_get_direct_page_vector(const char __user *data, + int num_pages, + loff_t off, size_t len); +extern void ceph_put_page_vector(struct page **pages, int num_pages); +extern void ceph_release_page_vector(struct page **pages, int num_pages); +extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); +extern int ceph_copy_user_to_page_vector(struct page **pages, + const char __user *data, + loff_t off, size_t len); +extern int ceph_copy_to_page_vector(struct page **pages, + const char *data, + loff_t off, size_t len); +extern int ceph_copy_from_page_vector(struct page **pages, + char *data, + loff_t off, size_t len); +extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data, + loff_t off, size_t len); +extern void ceph_zero_page_vector_range(int off, int len, struct page **pages); + + +#endif /* _FS_CEPH_SUPER_H */ diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h new file mode 100644 index 000000000000..4c5cb0880bba --- /dev/null +++ b/include/linux/ceph/mdsmap.h @@ -0,0 +1,62 @@ +#ifndef _FS_CEPH_MDSMAP_H +#define _FS_CEPH_MDSMAP_H + +#include "types.h" + +/* + * mds map - describe servers in the mds cluster. + * + * we limit fields to those the client actually xcares about + */ +struct ceph_mds_info { + u64 global_id; + struct ceph_entity_addr addr; + s32 state; + int num_export_targets; + bool laggy; + u32 *export_targets; +}; + +struct ceph_mdsmap { + u32 m_epoch, m_client_epoch, m_last_failure; + u32 m_root; + u32 m_session_timeout; /* seconds */ + u32 m_session_autoclose; /* seconds */ + u64 m_max_file_size; + u32 m_max_mds; /* size of m_addr, m_state arrays */ + struct ceph_mds_info *m_info; + + /* which object pools file data can be stored in */ + int m_num_data_pg_pools; + u32 *m_data_pg_pools; + u32 m_cas_pg_pool; +}; + +static inline struct ceph_entity_addr * +ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) +{ + if (w >= m->m_max_mds) + return NULL; + return &m->m_info[w].addr; +} + +static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w) +{ + BUG_ON(w < 0); + if (w >= m->m_max_mds) + return CEPH_MDS_STATE_DNE; + return m->m_info[w].state; +} + +static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) +{ + if (w >= 0 && w < m->m_max_mds) + return m->m_info[w].laggy; + return false; +} + +extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m); +extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end); +extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m); + +#endif diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h new file mode 100644 index 000000000000..5956d62c3057 --- /dev/null +++ b/include/linux/ceph/messenger.h @@ -0,0 +1,261 @@ +#ifndef __FS_CEPH_MESSENGER_H +#define __FS_CEPH_MESSENGER_H + +#include <linux/kref.h> +#include <linux/mutex.h> +#include <linux/net.h> +#include <linux/radix-tree.h> +#include <linux/uio.h> +#include <linux/version.h> +#include <linux/workqueue.h> + +#include "types.h" +#include "buffer.h" + +struct ceph_msg; +struct ceph_connection; + +extern struct workqueue_struct *ceph_msgr_wq; /* receive work queue */ + +/* + * Ceph defines these callbacks for handling connection events. + */ +struct ceph_connection_operations { + struct ceph_connection *(*get)(struct ceph_connection *); + void (*put)(struct ceph_connection *); + + /* handle an incoming message. */ + void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m); + + /* authorize an outgoing connection */ + int (*get_authorizer) (struct ceph_connection *con, + void **buf, int *len, int *proto, + void **reply_buf, int *reply_len, int force_new); + int (*verify_authorizer_reply) (struct ceph_connection *con, int len); + int (*invalidate_authorizer)(struct ceph_connection *con); + + /* protocol version mismatch */ + void (*bad_proto) (struct ceph_connection *con); + + /* there was some error on the socket (disconnect, whatever) */ + void (*fault) (struct ceph_connection *con); + + /* a remote host as terminated a message exchange session, and messages + * we sent (or they tried to send us) may be lost. */ + void (*peer_reset) (struct ceph_connection *con); + + struct ceph_msg * (*alloc_msg) (struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip); +}; + +/* use format string %s%d */ +#define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num) + +struct ceph_messenger { + struct ceph_entity_inst inst; /* my name+address */ + struct ceph_entity_addr my_enc_addr; + struct page *zero_page; /* used in certain error cases */ + + bool nocrc; + + /* + * the global_seq counts connections i (attempt to) initiate + * in order to disambiguate certain connect race conditions. + */ + u32 global_seq; + spinlock_t global_seq_lock; + + u32 supported_features; + u32 required_features; +}; + +/* + * a single message. it contains a header (src, dest, message type, etc.), + * footer (crc values, mainly), a "front" message body, and possibly a + * data payload (stored in some number of pages). + */ +struct ceph_msg { + struct ceph_msg_header hdr; /* header */ + struct ceph_msg_footer footer; /* footer */ + struct kvec front; /* unaligned blobs of message */ + struct ceph_buffer *middle; + struct page **pages; /* data payload. NOT OWNER. */ + unsigned nr_pages; /* size of page array */ + struct ceph_pagelist *pagelist; /* instead of pages */ + struct list_head list_head; + struct kref kref; + struct bio *bio; /* instead of pages/pagelist */ + struct bio *bio_iter; /* bio iterator */ + int bio_seg; /* current bio segment */ + struct ceph_pagelist *trail; /* the trailing part of the data */ + bool front_is_vmalloc; + bool more_to_follow; + bool needs_out_seq; + int front_max; + + struct ceph_msgpool *pool; +}; + +struct ceph_msg_pos { + int page, page_pos; /* which page; offset in page */ + int data_pos; /* offset in data payload */ + int did_page_crc; /* true if we've calculated crc for current page */ +}; + +/* ceph connection fault delay defaults, for exponential backoff */ +#define BASE_DELAY_INTERVAL (HZ/2) +#define MAX_DELAY_INTERVAL (5 * 60 * HZ) + +/* + * ceph_connection state bit flags + * + * QUEUED and BUSY are used together to ensure that only a single + * thread is currently opening, reading or writing data to the socket. + */ +#define LOSSYTX 0 /* we can close channel or drop messages on errors */ +#define CONNECTING 1 +#define NEGOTIATING 2 +#define KEEPALIVE_PENDING 3 +#define WRITE_PENDING 4 /* we have data ready to send */ +#define QUEUED 5 /* there is work queued on this connection */ +#define BUSY 6 /* work is being done */ +#define STANDBY 8 /* no outgoing messages, socket closed. we keep + * the ceph_connection around to maintain shared + * state with the peer. */ +#define CLOSED 10 /* we've closed the connection */ +#define SOCK_CLOSED 11 /* socket state changed to closed */ +#define OPENING 13 /* open connection w/ (possibly new) peer */ +#define DEAD 14 /* dead, about to kfree */ + +/* + * A single connection with another host. + * + * We maintain a queue of outgoing messages, and some session state to + * ensure that we can preserve the lossless, ordered delivery of + * messages in the case of a TCP disconnect. + */ +struct ceph_connection { + void *private; + atomic_t nref; + + const struct ceph_connection_operations *ops; + + struct ceph_messenger *msgr; + struct socket *sock; + unsigned long state; /* connection state (see flags above) */ + const char *error_msg; /* error message, if any */ + + struct ceph_entity_addr peer_addr; /* peer address */ + struct ceph_entity_name peer_name; /* peer name */ + struct ceph_entity_addr peer_addr_for_me; + unsigned peer_features; + u32 connect_seq; /* identify the most recent connection + attempt for this connection, client */ + u32 peer_global_seq; /* peer's global seq for this connection */ + + int auth_retry; /* true if we need a newer authorizer */ + void *auth_reply_buf; /* where to put the authorizer reply */ + int auth_reply_buf_len; + + struct mutex mutex; + + /* out queue */ + struct list_head out_queue; + struct list_head out_sent; /* sending or sent but unacked */ + u64 out_seq; /* last message queued for send */ + bool out_keepalive_pending; + + u64 in_seq, in_seq_acked; /* last message received, acked */ + + /* connection negotiation temps */ + char in_banner[CEPH_BANNER_MAX_LEN]; + union { + struct { /* outgoing connection */ + struct ceph_msg_connect out_connect; + struct ceph_msg_connect_reply in_reply; + }; + struct { /* incoming */ + struct ceph_msg_connect in_connect; + struct ceph_msg_connect_reply out_reply; + }; + }; + struct ceph_entity_addr actual_peer_addr; + + /* message out temps */ + struct ceph_msg *out_msg; /* sending message (== tail of + out_sent) */ + bool out_msg_done; + struct ceph_msg_pos out_msg_pos; + + struct kvec out_kvec[8], /* sending header/footer data */ + *out_kvec_cur; + int out_kvec_left; /* kvec's left in out_kvec */ + int out_skip; /* skip this many bytes */ + int out_kvec_bytes; /* total bytes left */ + bool out_kvec_is_msg; /* kvec refers to out_msg */ + int out_more; /* there is more data after the kvecs */ + __le64 out_temp_ack; /* for writing an ack */ + + /* message in temps */ + struct ceph_msg_header in_hdr; + struct ceph_msg *in_msg; + struct ceph_msg_pos in_msg_pos; + u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ + + char in_tag; /* protocol control byte */ + int in_base_pos; /* bytes read */ + __le64 in_temp_ack; /* for reading an ack */ + + struct delayed_work work; /* send|recv work */ + unsigned long delay; /* current delay interval */ +}; + + +extern const char *ceph_pr_addr(const struct sockaddr_storage *ss); +extern int ceph_parse_ips(const char *c, const char *end, + struct ceph_entity_addr *addr, + int max_count, int *count); + + +extern int ceph_msgr_init(void); +extern void ceph_msgr_exit(void); +extern void ceph_msgr_flush(void); + +extern struct ceph_messenger *ceph_messenger_create( + struct ceph_entity_addr *myaddr, + u32 features, u32 required); +extern void ceph_messenger_destroy(struct ceph_messenger *); + +extern void ceph_con_init(struct ceph_messenger *msgr, + struct ceph_connection *con); +extern void ceph_con_open(struct ceph_connection *con, + struct ceph_entity_addr *addr); +extern bool ceph_con_opened(struct ceph_connection *con); +extern void ceph_con_close(struct ceph_connection *con); +extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg); +extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg); +extern void ceph_con_revoke_message(struct ceph_connection *con, + struct ceph_msg *msg); +extern void ceph_con_keepalive(struct ceph_connection *con); +extern struct ceph_connection *ceph_con_get(struct ceph_connection *con); +extern void ceph_con_put(struct ceph_connection *con); + +extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags); +extern void ceph_msg_kfree(struct ceph_msg *m); + + +static inline struct ceph_msg *ceph_msg_get(struct ceph_msg *msg) +{ + kref_get(&msg->kref); + return msg; +} +extern void ceph_msg_last_put(struct kref *kref); +static inline void ceph_msg_put(struct ceph_msg *msg) +{ + kref_put(&msg->kref, ceph_msg_last_put); +} + +extern void ceph_msg_dump(struct ceph_msg *msg); + +#endif diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h new file mode 100644 index 000000000000..545f85917780 --- /dev/null +++ b/include/linux/ceph/mon_client.h @@ -0,0 +1,122 @@ +#ifndef _FS_CEPH_MON_CLIENT_H +#define _FS_CEPH_MON_CLIENT_H + +#include <linux/completion.h> +#include <linux/kref.h> +#include <linux/rbtree.h> + +#include "messenger.h" + +struct ceph_client; +struct ceph_mount_args; +struct ceph_auth_client; + +/* + * The monitor map enumerates the set of all monitors. + */ +struct ceph_monmap { + struct ceph_fsid fsid; + u32 epoch; + u32 num_mon; + struct ceph_entity_inst mon_inst[0]; +}; + +struct ceph_mon_client; +struct ceph_mon_generic_request; + + +/* + * Generic mechanism for resending monitor requests. + */ +typedef void (*ceph_monc_request_func_t)(struct ceph_mon_client *monc, + int newmon); + +/* a pending monitor request */ +struct ceph_mon_request { + struct ceph_mon_client *monc; + struct delayed_work delayed_work; + unsigned long delay; + ceph_monc_request_func_t do_request; +}; + +/* + * ceph_mon_generic_request is being used for the statfs and poolop requests + * which are bening done a bit differently because we need to get data back + * to the caller + */ +struct ceph_mon_generic_request { + struct kref kref; + u64 tid; + struct rb_node node; + int result; + void *buf; + int buf_len; + struct completion completion; + struct ceph_msg *request; /* original request */ + struct ceph_msg *reply; /* and reply */ +}; + +struct ceph_mon_client { + struct ceph_client *client; + struct ceph_monmap *monmap; + + struct mutex mutex; + struct delayed_work delayed_work; + + struct ceph_auth_client *auth; + struct ceph_msg *m_auth, *m_auth_reply, *m_subscribe, *m_subscribe_ack; + int pending_auth; + + bool hunting; + int cur_mon; /* last monitor i contacted */ + unsigned long sub_sent, sub_renew_after; + struct ceph_connection *con; + bool have_fsid; + + /* pending generic requests */ + struct rb_root generic_request_tree; + int num_generic_requests; + u64 last_tid; + + /* mds/osd map */ + int want_mdsmap; + int want_next_osdmap; /* 1 = want, 2 = want+asked */ + u32 have_osdmap, have_mdsmap; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_file; +#endif +}; + +extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end); +extern int ceph_monmap_contains(struct ceph_monmap *m, + struct ceph_entity_addr *addr); + +extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl); +extern void ceph_monc_stop(struct ceph_mon_client *monc); + +/* + * The model here is to indicate that we need a new map of at least + * epoch @want, and also call in when we receive a map. We will + * periodically rerequest the map from the monitor cluster until we + * get what we want. + */ +extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have); +extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have); + +extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc); + +extern int ceph_monc_do_statfs(struct ceph_mon_client *monc, + struct ceph_statfs *buf); + +extern int ceph_monc_open_session(struct ceph_mon_client *monc); + +extern int ceph_monc_validate_auth(struct ceph_mon_client *monc); + +extern int ceph_monc_create_snapid(struct ceph_mon_client *monc, + u32 pool, u64 *snapid); + +extern int ceph_monc_delete_snapid(struct ceph_mon_client *monc, + u32 pool, u64 snapid); + +#endif diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h new file mode 100644 index 000000000000..a362605f9368 --- /dev/null +++ b/include/linux/ceph/msgpool.h @@ -0,0 +1,25 @@ +#ifndef _FS_CEPH_MSGPOOL +#define _FS_CEPH_MSGPOOL + +#include <linux/mempool.h> +#include "messenger.h" + +/* + * we use memory pools for preallocating messages we may receive, to + * avoid unexpected OOM conditions. + */ +struct ceph_msgpool { + const char *name; + mempool_t *pool; + int front_len; /* preallocated payload size */ +}; + +extern int ceph_msgpool_init(struct ceph_msgpool *pool, + int front_len, int size, bool blocking, + const char *name); +extern void ceph_msgpool_destroy(struct ceph_msgpool *pool); +extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *, + int front_len); +extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *); + +#endif diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h new file mode 100644 index 000000000000..680d3d648cac --- /dev/null +++ b/include/linux/ceph/msgr.h @@ -0,0 +1,175 @@ +#ifndef CEPH_MSGR_H +#define CEPH_MSGR_H + +/* + * Data types for message passing layer used by Ceph. + */ + +#define CEPH_MON_PORT 6789 /* default monitor port */ + +/* + * client-side processes will try to bind to ports in this + * range, simply for the benefit of tools like nmap or wireshark + * that would like to identify the protocol. + */ +#define CEPH_PORT_FIRST 6789 +#define CEPH_PORT_START 6800 /* non-monitors start here */ +#define CEPH_PORT_LAST 6900 + +/* + * tcp connection banner. include a protocol version. and adjust + * whenever the wire protocol changes. try to keep this string length + * constant. + */ +#define CEPH_BANNER "ceph v027" +#define CEPH_BANNER_MAX_LEN 30 + + +/* + * Rollover-safe type and comparator for 32-bit sequence numbers. + * Comparator returns -1, 0, or 1. + */ +typedef __u32 ceph_seq_t; + +static inline __s32 ceph_seq_cmp(__u32 a, __u32 b) +{ + return (__s32)a - (__s32)b; +} + + +/* + * entity_name -- logical name for a process participating in the + * network, e.g. 'mds0' or 'osd3'. + */ +struct ceph_entity_name { + __u8 type; /* CEPH_ENTITY_TYPE_* */ + __le64 num; +} __attribute__ ((packed)); + +#define CEPH_ENTITY_TYPE_MON 0x01 +#define CEPH_ENTITY_TYPE_MDS 0x02 +#define CEPH_ENTITY_TYPE_OSD 0x04 +#define CEPH_ENTITY_TYPE_CLIENT 0x08 +#define CEPH_ENTITY_TYPE_AUTH 0x20 + +#define CEPH_ENTITY_TYPE_ANY 0xFF + +extern const char *ceph_entity_type_name(int type); + +/* + * entity_addr -- network address + */ +struct ceph_entity_addr { + __le32 type; + __le32 nonce; /* unique id for process (e.g. pid) */ + struct sockaddr_storage in_addr; +} __attribute__ ((packed)); + +struct ceph_entity_inst { + struct ceph_entity_name name; + struct ceph_entity_addr addr; +} __attribute__ ((packed)); + + +/* used by message exchange protocol */ +#define CEPH_MSGR_TAG_READY 1 /* server->client: ready for messages */ +#define CEPH_MSGR_TAG_RESETSESSION 2 /* server->client: reset, try again */ +#define CEPH_MSGR_TAG_WAIT 3 /* server->client: wait for racing + incoming connection */ +#define CEPH_MSGR_TAG_RETRY_SESSION 4 /* server->client + cseq: try again + with higher cseq */ +#define CEPH_MSGR_TAG_RETRY_GLOBAL 5 /* server->client + gseq: try again + with higher gseq */ +#define CEPH_MSGR_TAG_CLOSE 6 /* closing pipe */ +#define CEPH_MSGR_TAG_MSG 7 /* message */ +#define CEPH_MSGR_TAG_ACK 8 /* message ack */ +#define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ +#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ +#define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ +#define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ + + +/* + * connection negotiation + */ +struct ceph_msg_connect { + __le64 features; /* supported feature bits */ + __le32 host_type; /* CEPH_ENTITY_TYPE_* */ + __le32 global_seq; /* count connections initiated by this host */ + __le32 connect_seq; /* count connections initiated in this session */ + __le32 protocol_version; + __le32 authorizer_protocol; + __le32 authorizer_len; + __u8 flags; /* CEPH_MSG_CONNECT_* */ +} __attribute__ ((packed)); + +struct ceph_msg_connect_reply { + __u8 tag; + __le64 features; /* feature bits for this session */ + __le32 global_seq; + __le32 connect_seq; + __le32 protocol_version; + __le32 authorizer_len; + __u8 flags; +} __attribute__ ((packed)); + +#define CEPH_MSG_CONNECT_LOSSY 1 /* messages i send may be safely dropped */ + + +/* + * message header + */ +struct ceph_msg_header_old { + __le64 seq; /* message seq# for this session */ + __le64 tid; /* transaction id */ + __le16 type; /* message type */ + __le16 priority; /* priority. higher value == higher priority */ + __le16 version; /* version of message encoding */ + + __le32 front_len; /* bytes in main payload */ + __le32 middle_len;/* bytes in middle payload */ + __le32 data_len; /* bytes of data payload */ + __le16 data_off; /* sender: include full offset; + receiver: mask against ~PAGE_MASK */ + + struct ceph_entity_inst src, orig_src; + __le32 reserved; + __le32 crc; /* header crc32c */ +} __attribute__ ((packed)); + +struct ceph_msg_header { + __le64 seq; /* message seq# for this session */ + __le64 tid; /* transaction id */ + __le16 type; /* message type */ + __le16 priority; /* priority. higher value == higher priority */ + __le16 version; /* version of message encoding */ + + __le32 front_len; /* bytes in main payload */ + __le32 middle_len;/* bytes in middle payload */ + __le32 data_len; /* bytes of data payload */ + __le16 data_off; /* sender: include full offset; + receiver: mask against ~PAGE_MASK */ + + struct ceph_entity_name src; + __le32 reserved; + __le32 crc; /* header crc32c */ +} __attribute__ ((packed)); + +#define CEPH_MSG_PRIO_LOW 64 +#define CEPH_MSG_PRIO_DEFAULT 127 +#define CEPH_MSG_PRIO_HIGH 196 +#define CEPH_MSG_PRIO_HIGHEST 255 + +/* + * follows data payload + */ +struct ceph_msg_footer { + __le32 front_crc, middle_crc, data_crc; + __u8 flags; +} __attribute__ ((packed)); + +#define CEPH_MSG_FOOTER_COMPLETE (1<<0) /* msg wasn't aborted */ +#define CEPH_MSG_FOOTER_NOCRC (1<<1) /* no data crc */ + + +#endif diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h new file mode 100644 index 000000000000..6c91fb032c39 --- /dev/null +++ b/include/linux/ceph/osd_client.h @@ -0,0 +1,234 @@ +#ifndef _FS_CEPH_OSD_CLIENT_H +#define _FS_CEPH_OSD_CLIENT_H + +#include <linux/completion.h> +#include <linux/kref.h> +#include <linux/mempool.h> +#include <linux/rbtree.h> + +#include "types.h" +#include "osdmap.h" +#include "messenger.h" + +struct ceph_msg; +struct ceph_snap_context; +struct ceph_osd_request; +struct ceph_osd_client; +struct ceph_authorizer; +struct ceph_pagelist; + +/* + * completion callback for async writepages + */ +typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *, + struct ceph_msg *); + +/* a given osd we're communicating with */ +struct ceph_osd { + atomic_t o_ref; + struct ceph_osd_client *o_osdc; + int o_osd; + int o_incarnation; + struct rb_node o_node; + struct ceph_connection o_con; + struct list_head o_requests; + struct list_head o_osd_lru; + struct ceph_authorizer *o_authorizer; + void *o_authorizer_buf, *o_authorizer_reply_buf; + size_t o_authorizer_buf_len, o_authorizer_reply_buf_len; + unsigned long lru_ttl; + int o_marked_for_keepalive; + struct list_head o_keepalive_item; +}; + +/* an in-flight request */ +struct ceph_osd_request { + u64 r_tid; /* unique for this client */ + struct rb_node r_node; + struct list_head r_req_lru_item; + struct list_head r_osd_item; + struct ceph_osd *r_osd; + struct ceph_pg r_pgid; + int r_pg_osds[CEPH_PG_MAX_SIZE]; + int r_num_pg_osds; + + struct ceph_connection *r_con_filling_msg; + + struct ceph_msg *r_request, *r_reply; + int r_result; + int r_flags; /* any additional flags for the osd */ + u32 r_sent; /* >0 if r_request is sending/sent */ + int r_got_reply; + + struct ceph_osd_client *r_osdc; + struct kref r_kref; + bool r_mempool; + struct completion r_completion, r_safe_completion; + ceph_osdc_callback_t r_callback, r_safe_callback; + struct ceph_eversion r_reassert_version; + struct list_head r_unsafe_item; + + struct inode *r_inode; /* for use by callbacks */ + void *r_priv; /* ditto */ + + char r_oid[40]; /* object name */ + int r_oid_len; + unsigned long r_stamp; /* send OR check time */ + bool r_resend; /* msg send failed, needs retry */ + + struct ceph_file_layout r_file_layout; + struct ceph_snap_context *r_snapc; /* snap context for writes */ + unsigned r_num_pages; /* size of page array (follows) */ + struct page **r_pages; /* pages for data payload */ + int r_pages_from_pool; + int r_own_pages; /* if true, i own page list */ +#ifdef CONFIG_BLOCK + struct bio *r_bio; /* instead of pages */ +#endif + + struct ceph_pagelist *r_trail; /* trailing part of the data */ +}; + +struct ceph_osd_client { + struct ceph_client *client; + + struct ceph_osdmap *osdmap; /* current map */ + struct rw_semaphore map_sem; + struct completion map_waiters; + u64 last_requested_map; + + struct mutex request_mutex; + struct rb_root osds; /* osds */ + struct list_head osd_lru; /* idle osds */ + u64 timeout_tid; /* tid of timeout triggering rq */ + u64 last_tid; /* tid of last request */ + struct rb_root requests; /* pending requests */ + struct list_head req_lru; /* pending requests lru */ + int num_requests; + struct delayed_work timeout_work; + struct delayed_work osds_timeout_work; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_file; +#endif + + mempool_t *req_mempool; + + struct ceph_msgpool msgpool_op; + struct ceph_msgpool msgpool_op_reply; +}; + +struct ceph_osd_req_op { + u16 op; /* CEPH_OSD_OP_* */ + u32 flags; /* CEPH_OSD_FLAG_* */ + union { + struct { + u64 offset, length; + u64 truncate_size; + u32 truncate_seq; + } extent; + struct { + const char *name; + u32 name_len; + const char *val; + u32 value_len; + __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ + __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ + } xattr; + struct { + const char *class_name; + __u8 class_len; + const char *method_name; + __u8 method_len; + __u8 argc; + const char *indata; + u32 indata_len; + } cls; + struct { + u64 cookie, count; + } pgls; + struct { + u64 snapid; + } snap; + }; + u32 payload_len; +}; + +extern int ceph_osdc_init(struct ceph_osd_client *osdc, + struct ceph_client *client); +extern void ceph_osdc_stop(struct ceph_osd_client *osdc); + +extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, + struct ceph_msg *msg); +extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, + struct ceph_msg *msg); + +extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc, + struct ceph_file_layout *layout, + u64 snapid, + u64 off, u64 *plen, u64 *bno, + struct ceph_osd_request *req, + struct ceph_osd_req_op *op); + +extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, + int flags, + struct ceph_snap_context *snapc, + struct ceph_osd_req_op *ops, + bool use_mempool, + gfp_t gfp_flags, + struct page **pages, + struct bio *bio); + +extern void ceph_osdc_build_request(struct ceph_osd_request *req, + u64 off, u64 *plen, + struct ceph_osd_req_op *src_ops, + struct ceph_snap_context *snapc, + struct timespec *mtime, + const char *oid, + int oid_len); + +extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, + struct ceph_file_layout *layout, + struct ceph_vino vino, + u64 offset, u64 *len, int op, int flags, + struct ceph_snap_context *snapc, + int do_sync, u32 truncate_seq, + u64 truncate_size, + struct timespec *mtime, + bool use_mempool, int num_reply); + +static inline void ceph_osdc_get_request(struct ceph_osd_request *req) +{ + kref_get(&req->r_kref); +} +extern void ceph_osdc_release_request(struct kref *kref); +static inline void ceph_osdc_put_request(struct ceph_osd_request *req) +{ + kref_put(&req->r_kref, ceph_osdc_release_request); +} + +extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req, + bool nofail); +extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req); +extern void ceph_osdc_sync(struct ceph_osd_client *osdc); + +extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + u64 off, u64 *plen, + u32 truncate_seq, u64 truncate_size, + struct page **pages, int nr_pages); + +extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + struct ceph_snap_context *sc, + u64 off, u64 len, + u32 truncate_seq, u64 truncate_size, + struct timespec *mtime, + struct page **pages, int nr_pages, + int flags, int do_sync, bool nofail); + +#endif + diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h new file mode 100644 index 000000000000..ba4c205cbb01 --- /dev/null +++ b/include/linux/ceph/osdmap.h @@ -0,0 +1,130 @@ +#ifndef _FS_CEPH_OSDMAP_H +#define _FS_CEPH_OSDMAP_H + +#include <linux/rbtree.h> +#include "types.h" +#include "ceph_fs.h" +#include <linux/crush/crush.h> + +/* + * The osd map describes the current membership of the osd cluster and + * specifies the mapping of objects to placement groups and placement + * groups to (sets of) osds. That is, it completely specifies the + * (desired) distribution of all data objects in the system at some + * point in time. + * + * Each map version is identified by an epoch, which increases monotonically. + * + * The map can be updated either via an incremental map (diff) describing + * the change between two successive epochs, or as a fully encoded map. + */ +struct ceph_pg_pool_info { + struct rb_node node; + int id; + struct ceph_pg_pool v; + int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask; + char *name; +}; + +struct ceph_pg_mapping { + struct rb_node node; + struct ceph_pg pgid; + int len; + int osds[]; +}; + +struct ceph_osdmap { + struct ceph_fsid fsid; + u32 epoch; + u32 mkfs_epoch; + struct ceph_timespec created, modified; + + u32 flags; /* CEPH_OSDMAP_* */ + + u32 max_osd; /* size of osd_state, _offload, _addr arrays */ + u8 *osd_state; /* CEPH_OSD_* */ + u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ + struct ceph_entity_addr *osd_addr; + + struct rb_root pg_temp; + struct rb_root pg_pools; + u32 pool_max; + + /* the CRUSH map specifies the mapping of placement groups to + * the list of osds that store+replicate them. */ + struct crush_map *crush; +}; + +/* + * file layout helpers + */ +#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) +#define ceph_file_layout_stripe_count(l) \ + ((__s32)le32_to_cpu((l).fl_stripe_count)) +#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) +#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) +#define ceph_file_layout_object_su(l) \ + ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) +#define ceph_file_layout_pg_preferred(l) \ + ((__s32)le32_to_cpu((l).fl_pg_preferred)) +#define ceph_file_layout_pg_pool(l) \ + ((__s32)le32_to_cpu((l).fl_pg_pool)) + +static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_stripe_unit) * + le32_to_cpu(l->fl_stripe_count); +} + +/* "period" == bytes before i start on a new set of objects */ +static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_object_size) * + le32_to_cpu(l->fl_stripe_count); +} + + +static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd) +{ + return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP); +} + +static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag) +{ + return map && (map->flags & flag); +} + +extern char *ceph_osdmap_state_str(char *str, int len, int state); + +static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, + int osd) +{ + if (osd >= map->max_osd) + return NULL; + return &map->osd_addr[osd]; +} + +extern struct ceph_osdmap *osdmap_decode(void **p, void *end); +extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, + struct ceph_osdmap *map, + struct ceph_messenger *msgr); +extern void ceph_osdmap_destroy(struct ceph_osdmap *map); + +/* calculate mapping of a file extent to an object */ +extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, + u64 off, u64 *plen, + u64 *bno, u64 *oxoff, u64 *oxlen); + +/* calculate mapping of object to a placement group */ +extern int ceph_calc_object_layout(struct ceph_object_layout *ol, + const char *oid, + struct ceph_file_layout *fl, + struct ceph_osdmap *osdmap); +extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, + int *acting); +extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, + struct ceph_pg pgid); + +extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); + +#endif diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h new file mode 100644 index 000000000000..9660d6b0a35d --- /dev/null +++ b/include/linux/ceph/pagelist.h @@ -0,0 +1,75 @@ +#ifndef __FS_CEPH_PAGELIST_H +#define __FS_CEPH_PAGELIST_H + +#include <linux/list.h> + +struct ceph_pagelist { + struct list_head head; + void *mapped_tail; + size_t length; + size_t room; + struct list_head free_list; + size_t num_pages_free; +}; + +struct ceph_pagelist_cursor { + struct ceph_pagelist *pl; /* pagelist, for error checking */ + struct list_head *page_lru; /* page in list */ + size_t room; /* room remaining to reset to */ +}; + +static inline void ceph_pagelist_init(struct ceph_pagelist *pl) +{ + INIT_LIST_HEAD(&pl->head); + pl->mapped_tail = NULL; + pl->length = 0; + pl->room = 0; + INIT_LIST_HEAD(&pl->free_list); + pl->num_pages_free = 0; +} + +extern int ceph_pagelist_release(struct ceph_pagelist *pl); + +extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l); + +extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space); + +extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl); + +extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl, + struct ceph_pagelist_cursor *c); + +extern int ceph_pagelist_truncate(struct ceph_pagelist *pl, + struct ceph_pagelist_cursor *c); + +static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v) +{ + __le64 ev = cpu_to_le64(v); + return ceph_pagelist_append(pl, &ev, sizeof(ev)); +} +static inline int ceph_pagelist_encode_32(struct ceph_pagelist *pl, u32 v) +{ + __le32 ev = cpu_to_le32(v); + return ceph_pagelist_append(pl, &ev, sizeof(ev)); +} +static inline int ceph_pagelist_encode_16(struct ceph_pagelist *pl, u16 v) +{ + __le16 ev = cpu_to_le16(v); + return ceph_pagelist_append(pl, &ev, sizeof(ev)); +} +static inline int ceph_pagelist_encode_8(struct ceph_pagelist *pl, u8 v) +{ + return ceph_pagelist_append(pl, &v, 1); +} +static inline int ceph_pagelist_encode_string(struct ceph_pagelist *pl, + char *s, size_t len) +{ + int ret = ceph_pagelist_encode_32(pl, len); + if (ret) + return ret; + if (len) + return ceph_pagelist_append(pl, s, len); + return 0; +} + +#endif diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h new file mode 100644 index 000000000000..6d5247f2e81b --- /dev/null +++ b/include/linux/ceph/rados.h @@ -0,0 +1,405 @@ +#ifndef CEPH_RADOS_H +#define CEPH_RADOS_H + +/* + * Data types for the Ceph distributed object storage layer RADOS + * (Reliable Autonomic Distributed Object Store). + */ + +#include "msgr.h" + +/* + * osdmap encoding versions + */ +#define CEPH_OSDMAP_INC_VERSION 5 +#define CEPH_OSDMAP_INC_VERSION_EXT 5 +#define CEPH_OSDMAP_VERSION 5 +#define CEPH_OSDMAP_VERSION_EXT 5 + +/* + * fs id + */ +struct ceph_fsid { + unsigned char fsid[16]; +}; + +static inline int ceph_fsid_compare(const struct ceph_fsid *a, + const struct ceph_fsid *b) +{ + return memcmp(a, b, sizeof(*a)); +} + +/* + * ino, object, etc. + */ +typedef __le64 ceph_snapid_t; +#define CEPH_SNAPDIR ((__u64)(-1)) /* reserved for hidden .snap dir */ +#define CEPH_NOSNAP ((__u64)(-2)) /* "head", "live" revision */ +#define CEPH_MAXSNAP ((__u64)(-3)) /* largest valid snapid */ + +struct ceph_timespec { + __le32 tv_sec; + __le32 tv_nsec; +} __attribute__ ((packed)); + + +/* + * object layout - how objects are mapped into PGs + */ +#define CEPH_OBJECT_LAYOUT_HASH 1 +#define CEPH_OBJECT_LAYOUT_LINEAR 2 +#define CEPH_OBJECT_LAYOUT_HASHINO 3 + +/* + * pg layout -- how PGs are mapped onto (sets of) OSDs + */ +#define CEPH_PG_LAYOUT_CRUSH 0 +#define CEPH_PG_LAYOUT_HASH 1 +#define CEPH_PG_LAYOUT_LINEAR 2 +#define CEPH_PG_LAYOUT_HYBRID 3 + +#define CEPH_PG_MAX_SIZE 16 /* max # osds in a single pg */ + +/* + * placement group. + * we encode this into one __le64. + */ +struct ceph_pg { + __le16 preferred; /* preferred primary osd */ + __le16 ps; /* placement seed */ + __le32 pool; /* object pool */ +} __attribute__ ((packed)); + +/* + * pg_pool is a set of pgs storing a pool of objects + * + * pg_num -- base number of pseudorandomly placed pgs + * + * pgp_num -- effective number when calculating pg placement. this + * is used for pg_num increases. new pgs result in data being "split" + * into new pgs. for this to proceed smoothly, new pgs are intiially + * colocated with their parents; that is, pgp_num doesn't increase + * until the new pgs have successfully split. only _then_ are the new + * pgs placed independently. + * + * lpg_num -- localized pg count (per device). replicas are randomly + * selected. + * + * lpgp_num -- as above. + */ +#define CEPH_PG_TYPE_REP 1 +#define CEPH_PG_TYPE_RAID4 2 +#define CEPH_PG_POOL_VERSION 2 +struct ceph_pg_pool { + __u8 type; /* CEPH_PG_TYPE_* */ + __u8 size; /* number of osds in each pg */ + __u8 crush_ruleset; /* crush placement rule */ + __u8 object_hash; /* hash mapping object name to ps */ + __le32 pg_num, pgp_num; /* number of pg's */ + __le32 lpg_num, lpgp_num; /* number of localized pg's */ + __le32 last_change; /* most recent epoch changed */ + __le64 snap_seq; /* seq for per-pool snapshot */ + __le32 snap_epoch; /* epoch of last snap */ + __le32 num_snaps; + __le32 num_removed_snap_intervals; /* if non-empty, NO per-pool snaps */ + __le64 auid; /* who owns the pg */ +} __attribute__ ((packed)); + +/* + * stable_mod func is used to control number of placement groups. + * similar to straight-up modulo, but produces a stable mapping as b + * increases over time. b is the number of bins, and bmask is the + * containing power of 2 minus 1. + * + * b <= bmask and bmask=(2**n)-1 + * e.g., b=12 -> bmask=15, b=123 -> bmask=127 + */ +static inline int ceph_stable_mod(int x, int b, int bmask) +{ + if ((x & bmask) < b) + return x & bmask; + else + return x & (bmask >> 1); +} + +/* + * object layout - how a given object should be stored. + */ +struct ceph_object_layout { + struct ceph_pg ol_pgid; /* raw pg, with _full_ ps precision. */ + __le32 ol_stripe_unit; /* for per-object parity, if any */ +} __attribute__ ((packed)); + +/* + * compound epoch+version, used by storage layer to serialize mutations + */ +struct ceph_eversion { + __le32 epoch; + __le64 version; +} __attribute__ ((packed)); + +/* + * osd map bits + */ + +/* status bits */ +#define CEPH_OSD_EXISTS 1 +#define CEPH_OSD_UP 2 + +/* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */ +#define CEPH_OSD_IN 0x10000 +#define CEPH_OSD_OUT 0 + + +/* + * osd map flag bits + */ +#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */ +#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */ +#define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */ +#define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */ +#define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */ + +/* + * osd ops + */ +#define CEPH_OSD_OP_MODE 0xf000 +#define CEPH_OSD_OP_MODE_RD 0x1000 +#define CEPH_OSD_OP_MODE_WR 0x2000 +#define CEPH_OSD_OP_MODE_RMW 0x3000 +#define CEPH_OSD_OP_MODE_SUB 0x4000 + +#define CEPH_OSD_OP_TYPE 0x0f00 +#define CEPH_OSD_OP_TYPE_LOCK 0x0100 +#define CEPH_OSD_OP_TYPE_DATA 0x0200 +#define CEPH_OSD_OP_TYPE_ATTR 0x0300 +#define CEPH_OSD_OP_TYPE_EXEC 0x0400 +#define CEPH_OSD_OP_TYPE_PG 0x0500 + +enum { + /** data **/ + /* read */ + CEPH_OSD_OP_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1, + CEPH_OSD_OP_STAT = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2, + + /* fancy read */ + CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4, + + /* write */ + CEPH_OSD_OP_WRITE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1, + CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2, + CEPH_OSD_OP_TRUNCATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3, + CEPH_OSD_OP_ZERO = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4, + CEPH_OSD_OP_DELETE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5, + + /* fancy write */ + CEPH_OSD_OP_APPEND = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6, + CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7, + CEPH_OSD_OP_SETTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8, + CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9, + + CEPH_OSD_OP_TMAPUP = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10, + CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11, + CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12, + + CEPH_OSD_OP_CREATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13, + CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14, + + /** attrs **/ + /* read */ + CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1, + CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2, + CEPH_OSD_OP_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3, + + /* write */ + CEPH_OSD_OP_SETXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1, + CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2, + CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3, + CEPH_OSD_OP_RMXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4, + + /** subop **/ + CEPH_OSD_OP_PULL = CEPH_OSD_OP_MODE_SUB | 1, + CEPH_OSD_OP_PUSH = CEPH_OSD_OP_MODE_SUB | 2, + CEPH_OSD_OP_BALANCEREADS = CEPH_OSD_OP_MODE_SUB | 3, + CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4, + CEPH_OSD_OP_SCRUB = CEPH_OSD_OP_MODE_SUB | 5, + + /** lock **/ + CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1, + CEPH_OSD_OP_WRUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2, + CEPH_OSD_OP_RDLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3, + CEPH_OSD_OP_RDUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4, + CEPH_OSD_OP_UPLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5, + CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6, + + /** exec **/ + CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1, + + /** pg **/ + CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1, +}; + +static inline int ceph_osd_op_type_lock(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK; +} +static inline int ceph_osd_op_type_data(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA; +} +static inline int ceph_osd_op_type_attr(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR; +} +static inline int ceph_osd_op_type_exec(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC; +} +static inline int ceph_osd_op_type_pg(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG; +} + +static inline int ceph_osd_op_mode_subop(int op) +{ + return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB; +} +static inline int ceph_osd_op_mode_read(int op) +{ + return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD; +} +static inline int ceph_osd_op_mode_modify(int op) +{ + return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR; +} + +/* + * note that the following tmap stuff is also defined in the ceph librados.h + * any modification here needs to be updated there + */ +#define CEPH_OSD_TMAP_HDR 'h' +#define CEPH_OSD_TMAP_SET 's' +#define CEPH_OSD_TMAP_RM 'r' + +extern const char *ceph_osd_op_name(int op); + + +/* + * osd op flags + * + * An op may be READ, WRITE, or READ|WRITE. + */ +enum { + CEPH_OSD_FLAG_ACK = 1, /* want (or is) "ack" ack */ + CEPH_OSD_FLAG_ONNVRAM = 2, /* want (or is) "onnvram" ack */ + CEPH_OSD_FLAG_ONDISK = 4, /* want (or is) "ondisk" ack */ + CEPH_OSD_FLAG_RETRY = 8, /* resend attempt */ + CEPH_OSD_FLAG_READ = 16, /* op may read */ + CEPH_OSD_FLAG_WRITE = 32, /* op may write */ + CEPH_OSD_FLAG_ORDERSNAP = 64, /* EOLDSNAP if snapc is out of order */ + CEPH_OSD_FLAG_PEERSTAT = 128, /* msg includes osd_peer_stat */ + CEPH_OSD_FLAG_BALANCE_READS = 256, + CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */ + CEPH_OSD_FLAG_PGOP = 1024, /* pg op, no object */ + CEPH_OSD_FLAG_EXEC = 2048, /* op may exec */ + CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */ +}; + +enum { + CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ +}; + +#define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ +#define EBLACKLISTED ESHUTDOWN /* blacklisted */ + +/* xattr comparison */ +enum { + CEPH_OSD_CMPXATTR_OP_NOP = 0, + CEPH_OSD_CMPXATTR_OP_EQ = 1, + CEPH_OSD_CMPXATTR_OP_NE = 2, + CEPH_OSD_CMPXATTR_OP_GT = 3, + CEPH_OSD_CMPXATTR_OP_GTE = 4, + CEPH_OSD_CMPXATTR_OP_LT = 5, + CEPH_OSD_CMPXATTR_OP_LTE = 6 +}; + +enum { + CEPH_OSD_CMPXATTR_MODE_STRING = 1, + CEPH_OSD_CMPXATTR_MODE_U64 = 2 +}; + +/* + * an individual object operation. each may be accompanied by some data + * payload + */ +struct ceph_osd_op { + __le16 op; /* CEPH_OSD_OP_* */ + __le32 flags; /* CEPH_OSD_FLAG_* */ + union { + struct { + __le64 offset, length; + __le64 truncate_size; + __le32 truncate_seq; + } __attribute__ ((packed)) extent; + struct { + __le32 name_len; + __le32 value_len; + __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ + __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ + } __attribute__ ((packed)) xattr; + struct { + __u8 class_len; + __u8 method_len; + __u8 argc; + __le32 indata_len; + } __attribute__ ((packed)) cls; + struct { + __le64 cookie, count; + } __attribute__ ((packed)) pgls; + struct { + __le64 snapid; + } __attribute__ ((packed)) snap; + }; + __le32 payload_len; +} __attribute__ ((packed)); + +/* + * osd request message header. each request may include multiple + * ceph_osd_op object operations. + */ +struct ceph_osd_request_head { + __le32 client_inc; /* client incarnation */ + struct ceph_object_layout layout; /* pgid */ + __le32 osdmap_epoch; /* client's osdmap epoch */ + + __le32 flags; + + struct ceph_timespec mtime; /* for mutations only */ + struct ceph_eversion reassert_version; /* if we are replaying op */ + + __le32 object_len; /* length of object name */ + + __le64 snapid; /* snapid to read */ + __le64 snap_seq; /* writer's snap context */ + __le32 num_snaps; + + __le16 num_ops; + struct ceph_osd_op ops[]; /* followed by ops[], obj, ticket, snaps */ +} __attribute__ ((packed)); + +struct ceph_osd_reply_head { + __le32 client_inc; /* client incarnation */ + __le32 flags; + struct ceph_object_layout layout; + __le32 osdmap_epoch; + struct ceph_eversion reassert_version; /* for replaying uncommitted */ + + __le32 result; /* result code */ + + __le32 object_len; /* length of object name */ + __le32 num_ops; + struct ceph_osd_op ops[0]; /* ops[], object */ +} __attribute__ ((packed)); + + +#endif diff --git a/include/linux/ceph/types.h b/include/linux/ceph/types.h new file mode 100644 index 000000000000..28b35a005ec2 --- /dev/null +++ b/include/linux/ceph/types.h @@ -0,0 +1,29 @@ +#ifndef _FS_CEPH_TYPES_H +#define _FS_CEPH_TYPES_H + +/* needed before including ceph_fs.h */ +#include <linux/in.h> +#include <linux/types.h> +#include <linux/fcntl.h> +#include <linux/string.h> + +#include "ceph_fs.h" +#include "ceph_frag.h" +#include "ceph_hash.h" + +/* + * Identify inodes by both their ino AND snapshot id (a u64). + */ +struct ceph_vino { + u64 ino; + u64 snap; +}; + + +/* context for the caps reservation mechanism */ +struct ceph_cap_reservation { + int count; +}; + + +#endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0c991023ee47..709dfb901d11 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -75,7 +75,7 @@ struct cgroup_subsys_state { unsigned long flags; /* ID for this css, if possible */ - struct css_id *id; + struct css_id __rcu *id; }; /* bits in struct cgroup_subsys_state flags field */ @@ -205,7 +205,7 @@ struct cgroup { struct list_head children; /* my children */ struct cgroup *parent; /* my parent */ - struct dentry *dentry; /* cgroup fs entry, RCU protected */ + struct dentry __rcu *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c1a62c56a660..320d6c94ff84 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -16,7 +16,11 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +#ifdef CONFIG_SPARSE_RCU_POINTER +# define __rcu __attribute__((noderef, address_space(4))) +#else # define __rcu +#endif extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else diff --git a/include/linux/cred.h b/include/linux/cred.h index 4d2c39573f36..4aaeab376446 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -84,7 +84,7 @@ struct thread_group_cred { atomic_t usage; pid_t tgid; /* thread group process ID */ spinlock_t lock; - struct key *session_keyring; /* keyring inherited over fork */ + struct key __rcu *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct rcu_head rcu; /* RCU deletion hook */ }; diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h new file mode 100644 index 000000000000..97e435b191f4 --- /dev/null +++ b/include/linux/crush/crush.h @@ -0,0 +1,180 @@ +#ifndef CEPH_CRUSH_CRUSH_H +#define CEPH_CRUSH_CRUSH_H + +#include <linux/types.h> + +/* + * CRUSH is a pseudo-random data distribution algorithm that + * efficiently distributes input values (typically, data objects) + * across a heterogeneous, structured storage cluster. + * + * The algorithm was originally described in detail in this paper + * (although the algorithm has evolved somewhat since then): + * + * http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf + * + * LGPL2 + */ + + +#define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ + + +#define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ +#define CRUSH_MAX_SET 10 /* max size of a mapping result */ + + +/* + * CRUSH uses user-defined "rules" to describe how inputs should be + * mapped to devices. A rule consists of sequence of steps to perform + * to generate the set of output devices. + */ +struct crush_rule_step { + __u32 op; + __s32 arg1; + __s32 arg2; +}; + +/* step op codes */ +enum { + CRUSH_RULE_NOOP = 0, + CRUSH_RULE_TAKE = 1, /* arg1 = value to start with */ + CRUSH_RULE_CHOOSE_FIRSTN = 2, /* arg1 = num items to pick */ + /* arg2 = type */ + CRUSH_RULE_CHOOSE_INDEP = 3, /* same */ + CRUSH_RULE_EMIT = 4, /* no args */ + CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6, + CRUSH_RULE_CHOOSE_LEAF_INDEP = 7, +}; + +/* + * for specifying choose num (arg1) relative to the max parameter + * passed to do_rule + */ +#define CRUSH_CHOOSE_N 0 +#define CRUSH_CHOOSE_N_MINUS(x) (-(x)) + +/* + * The rule mask is used to describe what the rule is intended for. + * Given a ruleset and size of output set, we search through the + * rule list for a matching rule_mask. + */ +struct crush_rule_mask { + __u8 ruleset; + __u8 type; + __u8 min_size; + __u8 max_size; +}; + +struct crush_rule { + __u32 len; + struct crush_rule_mask mask; + struct crush_rule_step steps[0]; +}; + +#define crush_rule_size(len) (sizeof(struct crush_rule) + \ + (len)*sizeof(struct crush_rule_step)) + + + +/* + * A bucket is a named container of other items (either devices or + * other buckets). Items within a bucket are chosen using one of a + * few different algorithms. The table summarizes how the speed of + * each option measures up against mapping stability when items are + * added or removed. + * + * Bucket Alg Speed Additions Removals + * ------------------------------------------------ + * uniform O(1) poor poor + * list O(n) optimal poor + * tree O(log n) good good + * straw O(n) optimal optimal + */ +enum { + CRUSH_BUCKET_UNIFORM = 1, + CRUSH_BUCKET_LIST = 2, + CRUSH_BUCKET_TREE = 3, + CRUSH_BUCKET_STRAW = 4 +}; +extern const char *crush_bucket_alg_name(int alg); + +struct crush_bucket { + __s32 id; /* this'll be negative */ + __u16 type; /* non-zero; type=0 is reserved for devices */ + __u8 alg; /* one of CRUSH_BUCKET_* */ + __u8 hash; /* which hash function to use, CRUSH_HASH_* */ + __u32 weight; /* 16-bit fixed point */ + __u32 size; /* num items */ + __s32 *items; + + /* + * cached random permutation: used for uniform bucket and for + * the linear search fallback for the other bucket types. + */ + __u32 perm_x; /* @x for which *perm is defined */ + __u32 perm_n; /* num elements of *perm that are permuted/defined */ + __u32 *perm; +}; + +struct crush_bucket_uniform { + struct crush_bucket h; + __u32 item_weight; /* 16-bit fixed point; all items equally weighted */ +}; + +struct crush_bucket_list { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ + __u32 *sum_weights; /* 16-bit fixed point. element i is sum + of weights 0..i, inclusive */ +}; + +struct crush_bucket_tree { + struct crush_bucket h; /* note: h.size is _tree_ size, not number of + actual items */ + __u8 num_nodes; + __u32 *node_weights; +}; + +struct crush_bucket_straw { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ + __u32 *straws; /* 16-bit fixed point */ +}; + + + +/* + * CRUSH map includes all buckets, rules, etc. + */ +struct crush_map { + struct crush_bucket **buckets; + struct crush_rule **rules; + + /* + * Parent pointers to identify the parent bucket a device or + * bucket in the hierarchy. If an item appears more than + * once, this is the _last_ time it appeared (where buckets + * are processed in bucket id order, from -1 on down to + * -max_buckets. + */ + __u32 *bucket_parents; + __u32 *device_parents; + + __s32 max_buckets; + __u32 max_rules; + __s32 max_devices; +}; + + +/* crush.c */ +extern int crush_get_bucket_item_weight(struct crush_bucket *b, int pos); +extern void crush_calc_parents(struct crush_map *map); +extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b); +extern void crush_destroy_bucket_list(struct crush_bucket_list *b); +extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b); +extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b); +extern void crush_destroy_bucket(struct crush_bucket *b); +extern void crush_destroy(struct crush_map *map); + +#endif diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h new file mode 100644 index 000000000000..91e884230d5d --- /dev/null +++ b/include/linux/crush/hash.h @@ -0,0 +1,17 @@ +#ifndef CEPH_CRUSH_HASH_H +#define CEPH_CRUSH_HASH_H + +#define CRUSH_HASH_RJENKINS1 0 + +#define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1 + +extern const char *crush_hash_name(int type); + +extern __u32 crush_hash32(int type, __u32 a); +extern __u32 crush_hash32_2(int type, __u32 a, __u32 b); +extern __u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c); +extern __u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d); +extern __u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, + __u32 e); + +#endif diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h new file mode 100644 index 000000000000..c46b99c18bb0 --- /dev/null +++ b/include/linux/crush/mapper.h @@ -0,0 +1,20 @@ +#ifndef CEPH_CRUSH_MAPPER_H +#define CEPH_CRUSH_MAPPER_H + +/* + * CRUSH functions for find rules and then mapping an input to an + * output set. + * + * LGPL2 + */ + +#include "crush.h" + +extern int crush_find_rule(struct crush_map *map, int pool, int type, int size); +extern int crush_do_rule(struct crush_map *map, + int ruleno, + int x, int *result, int result_max, + int forcefeed, /* -1 for none */ + __u32 *weights); + +#endif diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 29b3ce3f2a1d..2833452ea01c 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -49,7 +49,6 @@ struct task_struct; #ifdef CONFIG_LOCKDEP extern void debug_show_all_locks(void); -extern void __debug_show_held_locks(struct task_struct *task); extern void debug_show_held_locks(struct task_struct *task); extern void debug_check_no_locks_freed(const void *from, unsigned long len); extern void debug_check_no_locks_held(struct task_struct *task); @@ -58,10 +57,6 @@ static inline void debug_show_all_locks(void) { } -static inline void __debug_show_held_locks(struct task_struct *task) -{ -} - static inline void debug_show_held_locks(struct task_struct *task) { } diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 52c0da4bdd18..bef3cda44c4c 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -1,6 +1,8 @@ #ifndef _DYNAMIC_DEBUG_H #define _DYNAMIC_DEBUG_H +#include <linux/jump_label.h> + /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They * use independent hash functions, to reduce the chance of false positives. @@ -22,8 +24,6 @@ struct _ddebug { const char *function; const char *filename; const char *format; - char primary_hash; - char secondary_hash; unsigned int lineno:24; /* * The flags field controls the behaviour at the callsite. @@ -33,6 +33,7 @@ struct _ddebug { #define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ #define _DPRINTK_FLAGS_DEFAULT 0 unsigned int flags:8; + char enabled; } __attribute__((aligned(8))); @@ -42,33 +43,35 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, #if defined(CONFIG_DYNAMIC_DEBUG) extern int ddebug_remove_module(const char *mod_name); -#define __dynamic_dbg_enabled(dd) ({ \ - int __ret = 0; \ - if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) && \ - (dynamic_debug_enabled2 & (1LL << DEBUG_HASH2)))) \ - if (unlikely(dd.flags)) \ - __ret = 1; \ - __ret; }) - #define dynamic_pr_debug(fmt, ...) do { \ + __label__ do_printk; \ + __label__ out; \ static struct _ddebug descriptor \ __used \ __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ - DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ - if (__dynamic_dbg_enabled(descriptor)) \ - printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ + _DPRINTK_FLAGS_DEFAULT }; \ + JUMP_LABEL(&descriptor.enabled, do_printk); \ + goto out; \ +do_printk: \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ +out: ; \ } while (0) #define dynamic_dev_dbg(dev, fmt, ...) do { \ + __label__ do_printk; \ + __label__ out; \ static struct _ddebug descriptor \ __used \ __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ - DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ - if (__dynamic_dbg_enabled(descriptor)) \ - dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ + _DPRINTK_FLAGS_DEFAULT }; \ + JUMP_LABEL(&descriptor.enabled, do_printk); \ + goto out; \ +do_printk: \ + dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ +out: ; \ } while (0) #else diff --git a/include/linux/edac.h b/include/linux/edac.h index 7cf92e8a4196..36c66443bdfd 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -13,6 +13,7 @@ #define _LINUX_EDAC_H_ #include <asm/atomic.h> +#include <linux/sysdev.h> #define EDAC_OPSTATE_INVAL -1 #define EDAC_OPSTATE_POLL 0 @@ -22,9 +23,12 @@ extern int edac_op_state; extern int edac_err_assert; extern atomic_t edac_handlers; +extern struct sysdev_class edac_class; extern int edac_handler_set(void); extern void edac_atomic_assert_error(void); +extern struct sysdev_class *edac_get_sysfs_class(void); +extern void edac_put_sysfs_class(void); static inline void opstate_init(void) { diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index f59ed297b661..133c0ba25e30 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -31,7 +31,7 @@ struct embedded_fd_set { struct fdtable { unsigned int max_fds; - struct file ** fd; /* current fd array */ + struct file __rcu **fd; /* current fd array */ fd_set *close_on_exec; fd_set *open_fds; struct rcu_head rcu; @@ -46,7 +46,7 @@ struct files_struct { * read mostly part */ atomic_t count; - struct fdtable *fdt; + struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP @@ -55,7 +55,7 @@ struct files_struct { int next_fd; struct embedded_fd_set close_on_exec_init; struct embedded_fd_set open_fds_init; - struct file * fd_array[NR_OPEN_DEFAULT]; + struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; #define rcu_dereference_check_fdtable(files, fdtfd) \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 63d069bd80b7..3168dcfb94f2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1384,7 +1384,7 @@ struct super_block { * Saved mount options for lazy filesystems using * generic_show_options() */ - char *s_options; + char __rcu *s_options; }; extern struct timespec current_fs_time(struct super_block *sb); diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 02b8b24f8f51..8beabb958f61 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -191,8 +191,8 @@ struct ftrace_event_call { unsigned int flags; #ifdef CONFIG_PERF_EVENTS - int perf_refcount; - struct hlist_head *perf_events; + int perf_refcount; + struct hlist_head __percpu *perf_events; #endif }; @@ -252,8 +252,8 @@ DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); -extern int perf_trace_enable(struct perf_event *event); -extern void perf_trace_disable(struct perf_event *event); +extern int perf_trace_add(struct perf_event *event, int flags); +extern void perf_trace_del(struct perf_event *event, int flags); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 5f2f4c4d8fb0..af3f06b41dc1 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -129,8 +129,8 @@ struct blk_scsi_cmd_filter { struct disk_part_tbl { struct rcu_head rcu_head; int len; - struct hd_struct *last_lookup; - struct hd_struct *part[]; + struct hd_struct __rcu *last_lookup; + struct hd_struct __rcu *part[]; }; struct gendisk { @@ -149,7 +149,7 @@ struct gendisk { * non-critical accesses use RCU. Always access through * helpers. */ - struct disk_part_tbl *part_tbl; + struct disk_part_tbl __rcu *part_tbl; struct hd_struct part0; const struct block_device_operations *fops; diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index d5b387669dab..96c323ac44df 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -64,6 +64,8 @@ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + #ifndef PREEMPT_ACTIVE #define PREEMPT_ACTIVE_BITS 1 #define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) @@ -82,10 +84,13 @@ /* * Are we doing bottom half or hardware interrupt processing? * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? */ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) /* * Are we in NMI context? @@ -132,14 +137,16 @@ extern void synchronize_irq(unsigned int irq); struct task_struct; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING) static inline void account_system_vtime(struct task_struct *tsk) { } +#else +extern void account_system_vtime(struct task_struct *tsk); #endif #if defined(CONFIG_NO_HZ) -#if defined(CONFIG_TINY_RCU) +#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU) extern void rcu_enter_nohz(void); extern void rcu_exit_nohz(void); diff --git a/include/linux/idr.h b/include/linux/idr.h index e968db71e33a..cdb715e58e3e 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -50,14 +50,14 @@ struct idr_layer { unsigned long bitmap; /* A zero bit means "space here" */ - struct idr_layer *ary[1<<IDR_BITS]; + struct idr_layer __rcu *ary[1<<IDR_BITS]; int count; /* When zero, we can release it */ int layer; /* distance from leaf */ struct rcu_head rcu_head; }; struct idr { - struct idr_layer *top; + struct idr_layer __rcu *top; struct idr_layer *id_free; int layers; /* only valid without concurrent changes */ int id_free_cnt; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1f43fa56f600..2fea6c8ef6ba 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -82,11 +82,17 @@ extern struct group_info init_groups; # define CAP_INIT_BSET CAP_FULL_SET #ifdef CONFIG_TREE_PREEMPT_RCU +#define INIT_TASK_RCU_TREE_PREEMPT() \ + .rcu_blocked_node = NULL, +#else +#define INIT_TASK_RCU_TREE_PREEMPT(tsk) +#endif +#ifdef CONFIG_PREEMPT_RCU #define INIT_TASK_RCU_PREEMPT(tsk) \ .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ - .rcu_blocked_node = NULL, \ - .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), + .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ + INIT_TASK_RCU_TREE_PREEMPT() #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif @@ -137,8 +143,8 @@ extern struct cred init_cred; .children = LIST_HEAD_INIT(tsk.children), \ .sibling = LIST_HEAD_INIT(tsk.sibling), \ .group_leader = &tsk, \ - .real_cred = &init_cred, \ - .cred = &init_cred, \ + RCU_INIT_POINTER(.real_cred, &init_cred), \ + RCU_INIT_POINTER(.cred, &init_cred), \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(tsk.cred_guard_mutex), \ .comm = "swapper", \ diff --git a/include/linux/input.h b/include/linux/input.h index 896a92227bc4..d6ae1761be97 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1196,7 +1196,7 @@ struct input_dev { int (*flush)(struct input_dev *dev, struct file *file); int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value); - struct input_handle *grab; + struct input_handle __rcu *grab; spinlock_t event_lock; struct mutex mutex; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 19988983aeac..414328577ced 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -18,6 +18,7 @@ #include <asm/atomic.h> #include <asm/ptrace.h> #include <asm/system.h> +#include <trace/events/irq.h> /* * These correspond to the IORESOURCE_IRQ_* defines in @@ -407,7 +408,12 @@ asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); -#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0) +static inline void __raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL); + or_softirq_pending(1UL << nr); +} + extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); extern void wakeup_softirqd(void); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 64d529133031..3e70b21884a9 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -53,7 +53,7 @@ struct io_context { struct radix_tree_root radix_root; struct hlist_head cic_list; - void *ioc_data; + void __rcu *ioc_data; }; static inline struct io_context *ioc_task_link(struct io_context *ioc) diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h new file mode 100644 index 000000000000..4fa09d4d0b71 --- /dev/null +++ b/include/linux/irq_work.h @@ -0,0 +1,20 @@ +#ifndef _LINUX_IRQ_WORK_H +#define _LINUX_IRQ_WORK_H + +struct irq_work { + struct irq_work *next; + void (*func)(struct irq_work *); +}; + +static inline +void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *)) +{ + entry->next = NULL; + entry->func = func; +} + +bool irq_work_queue(struct irq_work *entry); +void irq_work_run(void); +void irq_work_sync(struct irq_work *entry); + +#endif /* _LINUX_IRQ_WORK_H */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h new file mode 100644 index 000000000000..b67cb180e6e9 --- /dev/null +++ b/include/linux/jump_label.h @@ -0,0 +1,74 @@ +#ifndef _LINUX_JUMP_LABEL_H +#define _LINUX_JUMP_LABEL_H + +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL) +# include <asm/jump_label.h> +# define HAVE_JUMP_LABEL +#endif + +enum jump_label_type { + JUMP_LABEL_ENABLE, + JUMP_LABEL_DISABLE +}; + +struct module; + +#ifdef HAVE_JUMP_LABEL + +extern struct jump_entry __start___jump_table[]; +extern struct jump_entry __stop___jump_table[]; + +extern void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type); +extern void arch_jump_label_text_poke_early(jump_label_t addr); +extern void jump_label_update(unsigned long key, enum jump_label_type type); +extern void jump_label_apply_nops(struct module *mod); +extern int jump_label_text_reserved(void *start, void *end); + +#define jump_label_enable(key) \ + jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE); + +#define jump_label_disable(key) \ + jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE); + +#else + +#define JUMP_LABEL(key, label) \ +do { \ + if (unlikely(*key)) \ + goto label; \ +} while (0) + +#define jump_label_enable(cond_var) \ +do { \ + *(cond_var) = 1; \ +} while (0) + +#define jump_label_disable(cond_var) \ +do { \ + *(cond_var) = 0; \ +} while (0) + +static inline int jump_label_apply_nops(struct module *mod) +{ + return 0; +} + +static inline int jump_label_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif + +#define COND_STMT(key, stmt) \ +do { \ + __label__ jl_enabled; \ + JUMP_LABEL(key, jl_enabled); \ + if (0) { \ +jl_enabled: \ + stmt; \ + } \ +} while (0) + +#endif diff --git a/include/linux/jump_label_ref.h b/include/linux/jump_label_ref.h new file mode 100644 index 000000000000..e5d012ad92c6 --- /dev/null +++ b/include/linux/jump_label_ref.h @@ -0,0 +1,44 @@ +#ifndef _LINUX_JUMP_LABEL_REF_H +#define _LINUX_JUMP_LABEL_REF_H + +#include <linux/jump_label.h> +#include <asm/atomic.h> + +#ifdef HAVE_JUMP_LABEL + +static inline void jump_label_inc(atomic_t *key) +{ + if (atomic_add_return(1, key) == 1) + jump_label_enable(key); +} + +static inline void jump_label_dec(atomic_t *key) +{ + if (atomic_dec_and_test(key)) + jump_label_disable(key); +} + +#else /* !HAVE_JUMP_LABEL */ + +static inline void jump_label_inc(atomic_t *key) +{ + atomic_inc(key); +} + +static inline void jump_label_dec(atomic_t *key) +{ + atomic_dec(key); +} + +#undef JUMP_LABEL +#define JUMP_LABEL(key, label) \ +do { \ + if (unlikely(__builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(key), atomic_t *), \ + atomic_read((atomic_t *)(key)), *(key)))) \ + goto label; \ +} while (0) + +#endif /* HAVE_JUMP_LABEL */ + +#endif /* _LINUX_JUMP_LABEL_REF_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2b0a35e6bc69..1759ba5adce8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -58,7 +58,18 @@ extern const char linux_proc_banner[]; #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) -#define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) +#define roundup(x, y) ( \ +{ \ + typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#define rounddown(x, y) ( \ +{ \ + typeof(x) __x = (x); \ + __x - (__x % (y)); \ +} \ +) #define DIV_ROUND_CLOSEST(x, divisor)( \ { \ typeof(divisor) __divisor = divisor; \ diff --git a/include/linux/key.h b/include/linux/key.h index cd50dfa1d4c2..3db0adce1fda 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -178,8 +178,9 @@ struct key { */ union { unsigned long value; + void __rcu *rcudata; void *data; - struct keyring_list *subscriptions; + struct keyring_list __rcu *subscriptions; } payload; }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c13cc48697aa..ac740b26eb10 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -205,7 +205,7 @@ struct kvm { struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP - struct kvm_irq_routing_table *irq_routing; + struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head mask_notifier_list; struct hlist_head irq_ack_notifier_list; #endif diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 17d050ce7ab8..71c09b26c759 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -32,6 +32,17 @@ extern int lock_stat; #define MAX_LOCKDEP_SUBCLASSES 8UL /* + * NR_LOCKDEP_CACHING_CLASSES ... Number of classes + * cached in the instance of lockdep_map + * + * Currently main class (subclass == 0) and signle depth subclass + * are cached in lockdep_map. This optimization is mainly targeting + * on rq->lock. double_rq_lock() acquires this highly competitive with + * single depth. + */ +#define NR_LOCKDEP_CACHING_CLASSES 2 + +/* * Lock-classes are keyed via unique addresses, by embedding the * lockclass-key into the kernel (or module) .data section. (For * static locks we use the lock address itself as the key.) @@ -138,7 +149,7 @@ void clear_lock_stats(struct lock_class *class); */ struct lockdep_map { struct lock_class_key *key; - struct lock_class *class_cache; + struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; const char *name; #ifdef CONFIG_LOCK_STAT int cpu; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ee7e258627f9..cb57d657ce4d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -299,7 +299,7 @@ struct mm_struct { * new_owner->mm == mm * new_owner->alloc_lock is held */ - struct task_struct *owner; + struct task_struct __rcu *owner; #endif #ifdef CONFIG_PROC_FS diff --git a/include/linux/module.h b/include/linux/module.h index aace066bad8f..b29e7458b966 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -350,7 +350,10 @@ struct module struct tracepoint *tracepoints; unsigned int num_tracepoints; #endif - +#ifdef HAVE_JUMP_LABEL + struct jump_entry *jump_entries; + unsigned int num_jump_entries; +#endif #ifdef CONFIG_TRACING const char **trace_bprintk_fmt_start; unsigned int num_trace_bprintk_fmt; diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 9ed534c991b9..70cd0603911c 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -39,8 +39,9 @@ enum ctattr_type { CTA_TUPLE_MASTER, CTA_NAT_SEQ_ADJ_ORIG, CTA_NAT_SEQ_ADJ_REPLY, - CTA_SECMARK, + CTA_SECMARK, /* obsolete */ CTA_ZONE, + CTA_SECCTX, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -172,4 +173,11 @@ enum ctattr_help { }; #define CTA_HELP_MAX (__CTA_HELP_MAX - 1) +enum ctattr_secctx { + CTA_SECCTX_UNSPEC, + CTA_SECCTX_NAME, + __CTA_SECCTX_MAX +}; +#define CTA_SECCTX_MAX (__CTA_SECCTX_MAX - 1) + #endif /* _IPCONNTRACK_NETLINK_H */ diff --git a/include/linux/netfilter/xt_SECMARK.h b/include/linux/netfilter/xt_SECMARK.h index 6fcd3448b186..989092bd6274 100644 --- a/include/linux/netfilter/xt_SECMARK.h +++ b/include/linux/netfilter/xt_SECMARK.h @@ -11,18 +11,12 @@ * packets are being marked for. */ #define SECMARK_MODE_SEL 0x01 /* SELinux */ -#define SECMARK_SELCTX_MAX 256 - -struct xt_secmark_target_selinux_info { - __u32 selsid; - char selctx[SECMARK_SELCTX_MAX]; -}; +#define SECMARK_SECCTX_MAX 256 struct xt_secmark_target_info { __u8 mode; - union { - struct xt_secmark_target_selinux_info sel; - } u; + __u32 secid; + char secctx[SECMARK_SECCTX_MAX]; }; #endif /*_XT_SECMARK_H_target */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 508f8cf6da37..d0edf7d823ae 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -185,7 +185,7 @@ struct nfs_inode { struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ struct list_head open_states; - struct nfs_delegation *delegation; + struct nfs_delegation __rcu *delegation; fmode_t delegation_state; struct rw_semaphore rwsem; #endif /* CONFIG_NFS_V4*/ diff --git a/include/linux/notifier.h b/include/linux/notifier.h index b2f1a4d83550..2026f9e1ceb8 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -49,28 +49,28 @@ struct notifier_block { int (*notifier_call)(struct notifier_block *, unsigned long, void *); - struct notifier_block *next; + struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; - struct notifier_block *head; + struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; - struct notifier_block *head; + struct notifier_block __rcu *head; }; struct raw_notifier_head { - struct notifier_block *head; + struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_struct srcu; - struct notifier_block *head; + struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 5171639ecf0f..32fb81212fd1 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -15,6 +15,7 @@ #include <linux/types.h> #include <linux/spinlock.h> +#include <linux/init.h> #include <asm/atomic.h> /* Each escaped entry is prefixed by ESCAPE_CODE @@ -185,4 +186,10 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val); int oprofile_add_data64(struct op_entry *entry, u64 val); int oprofile_write_commit(struct op_entry *entry); +#ifdef CONFIG_PERF_EVENTS +int __init oprofile_perf_init(struct oprofile_operations *ops); +void oprofile_perf_exit(void); +char *op_name_from_perf_id(void); +#endif /* CONFIG_PERF_EVENTS */ + #endif /* OPROFILE_H */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 570fddeb0388..2615c37c8fe5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -517,6 +517,7 @@ #define PCI_DEVICE_ID_AMD_11H_NB_DRAM 0x1302 #define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303 #define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304 +#define PCI_DEVICE_ID_AMD_15H_NB_MISC 0x1603 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 #define PCI_DEVICE_ID_AMD_SCSI 0x2020 diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index ce2dc655cd1d..27ef6b190ea6 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -139,6 +139,15 @@ __aligned(PAGE_SIZE) /* + * Declaration/definition used for per-CPU variables that must be read mostly. + */ +#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, "..readmostly") + +#define DEFINE_PER_CPU_READ_MOSTLY(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, "..readmostly") + +/* * Intermodule exports for per-CPU variables. sparse forgets about * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to * noop if __CHECKER__. diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 49466b13c5c6..0eb50832aa00 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -39,6 +39,15 @@ preempt_enable(); \ } while (0) +#define get_cpu_ptr(var) ({ \ + preempt_disable(); \ + this_cpu_ptr(var); }) + +#define put_cpu_ptr(var) do { \ + (void)(var); \ + preempt_enable(); \ +} while (0) + #ifdef CONFIG_SMP /* minimum unit size, also is the maximum supported allocation size */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 716f99b682c1..057bf22a8323 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -486,6 +486,8 @@ struct perf_guest_info_callbacks { #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> +#include <linux/irq_work.h> +#include <linux/jump_label_ref.h> #include <asm/atomic.h> #include <asm/local.h> @@ -529,16 +531,22 @@ struct hw_perf_event { int last_cpu; }; struct { /* software */ - s64 remaining; struct hrtimer hrtimer; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ struct arch_hw_breakpoint info; struct list_head bp_list; + /* + * Crufty hack to avoid the chicken and egg + * problem hw_breakpoint has with context + * creation and event initalization. + */ + struct task_struct *bp_target; }; #endif }; + int state; local64_t prev_count; u64 sample_period; u64 last_period; @@ -550,6 +558,13 @@ struct hw_perf_event { #endif }; +/* + * hw_perf_event::state flags + */ +#define PERF_HES_STOPPED 0x01 /* the counter is stopped */ +#define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ +#define PERF_HES_ARCH 0x04 + struct perf_event; /* @@ -561,36 +576,70 @@ struct perf_event; * struct pmu - generic performance monitoring unit */ struct pmu { - int (*enable) (struct perf_event *event); - void (*disable) (struct perf_event *event); - int (*start) (struct perf_event *event); - void (*stop) (struct perf_event *event); - void (*read) (struct perf_event *event); - void (*unthrottle) (struct perf_event *event); + struct list_head entry; + + int * __percpu pmu_disable_count; + struct perf_cpu_context * __percpu pmu_cpu_context; + int task_ctx_nr; + + /* + * Fully disable/enable this PMU, can be used to protect from the PMI + * as well as for lazy/batch writing of the MSRs. + */ + void (*pmu_enable) (struct pmu *pmu); /* optional */ + void (*pmu_disable) (struct pmu *pmu); /* optional */ /* - * Group events scheduling is treated as a transaction, add group - * events as a whole and perform one schedulability test. If the test - * fails, roll back the whole group + * Try and initialize the event for this PMU. + * Should return -ENOENT when the @event doesn't match this PMU. */ + int (*event_init) (struct perf_event *event); + +#define PERF_EF_START 0x01 /* start the counter when adding */ +#define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ +#define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* - * Start the transaction, after this ->enable() doesn't need - * to do schedulability tests. + * Adds/Removes a counter to/from the PMU, can be done inside + * a transaction, see the ->*_txn() methods. */ - void (*start_txn) (const struct pmu *pmu); + int (*add) (struct perf_event *event, int flags); + void (*del) (struct perf_event *event, int flags); + /* - * If ->start_txn() disabled the ->enable() schedulability test + * Starts/Stops a counter present on the PMU. The PMI handler + * should stop the counter when perf_event_overflow() returns + * !0. ->start() will be used to continue. + */ + void (*start) (struct perf_event *event, int flags); + void (*stop) (struct perf_event *event, int flags); + + /* + * Updates the counter value of the event. + */ + void (*read) (struct perf_event *event); + + /* + * Group events scheduling is treated as a transaction, add + * group events as a whole and perform one schedulability test. + * If the test fails, roll back the whole group + * + * Start the transaction, after this ->add() doesn't need to + * do schedulability tests. + */ + void (*start_txn) (struct pmu *pmu); /* optional */ + /* + * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. */ - int (*commit_txn) (const struct pmu *pmu); + int (*commit_txn) (struct pmu *pmu); /* optional */ /* - * Will cancel the transaction, assumes ->disable() is called for - * each successfull ->enable() during the transaction. + * Will cancel the transaction, assumes ->del() is called + * for each successfull ->add() during the transaction. */ - void (*cancel_txn) (const struct pmu *pmu); + void (*cancel_txn) (struct pmu *pmu); /* optional */ }; /** @@ -631,11 +680,6 @@ struct perf_buffer { void *data_pages[0]; }; -struct perf_pending_entry { - struct perf_pending_entry *next; - void (*func)(struct perf_pending_entry *); -}; - struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, int, @@ -656,6 +700,7 @@ struct swevent_hlist { #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 +#define PERF_ATTACH_TASK 0x04 /** * struct perf_event - performance event kernel representation: @@ -669,7 +714,7 @@ struct perf_event { int nr_siblings; int group_flags; struct perf_event *group_leader; - const struct pmu *pmu; + struct pmu *pmu; enum perf_event_active_state state; unsigned int attach_state; @@ -743,7 +788,7 @@ struct perf_event { int pending_wakeup; int pending_kill; int pending_disable; - struct perf_pending_entry pending; + struct irq_work pending; atomic_t event_limit; @@ -763,12 +808,19 @@ struct perf_event { #endif /* CONFIG_PERF_EVENTS */ }; +enum perf_event_context_type { + task_context, + cpu_context, +}; + /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { + enum perf_event_context_type type; + struct pmu *pmu; /* * Protect the states of the events in the list, * nr_active, and the list: @@ -808,6 +860,12 @@ struct perf_event_context { struct rcu_head rcu_head; }; +/* + * Number of contexts where an event can trigger: + * task, softirq, hardirq, nmi. + */ +#define PERF_NR_CONTEXTS 4 + /** * struct perf_event_cpu_context - per cpu event context structure */ @@ -815,18 +873,9 @@ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; - int max_pertask; int exclusive; - struct swevent_hlist *swevent_hlist; - struct mutex hlist_mutex; - int hlist_refcount; - - /* - * Recursion avoidance: - * - * task, softirq, irq, nmi context - */ - int recursion[4]; + struct list_head rotation_list; + int jiffies_interval; }; struct perf_output_handle { @@ -842,26 +891,34 @@ struct perf_output_handle { #ifdef CONFIG_PERF_EVENTS -/* - * Set by architecture code: - */ -extern int perf_max_events; +extern int perf_pmu_register(struct pmu *pmu); +extern void perf_pmu_unregister(struct pmu *pmu); + +extern int perf_num_counters(void); +extern const char *perf_pmu_name(void); +extern void __perf_event_task_sched_in(struct task_struct *task); +extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); -extern const struct pmu *hw_perf_event_init(struct perf_event *event); +extern atomic_t perf_task_events; + +static inline void perf_event_task_sched_in(struct task_struct *task) +{ + COND_STMT(&perf_task_events, __perf_event_task_sched_in(task)); +} + +static inline +void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) +{ + COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next)); +} -extern void perf_event_task_sched_in(struct task_struct *task); -extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); -extern void perf_event_task_tick(struct task_struct *task); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); -extern void set_perf_event_pending(void); -extern void perf_event_do_pending(void); +extern void perf_event_delayed_put(struct task_struct *task); extern void perf_event_print_debug(void); -extern void __perf_disable(void); -extern bool __perf_enable(void); -extern void perf_disable(void); -extern void perf_enable(void); +extern void perf_pmu_disable(struct pmu *pmu); +extern void perf_pmu_enable(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_event_update_userpage(struct perf_event *event); @@ -869,7 +926,7 @@ extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, - pid_t pid, + struct task_struct *task, perf_overflow_handler_t callback); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -920,14 +977,7 @@ extern int perf_event_overflow(struct perf_event *event, int nmi, */ static inline int is_software_event(struct perf_event *event) { - switch (event->attr.type) { - case PERF_TYPE_SOFTWARE: - case PERF_TYPE_TRACEPOINT: - /* for now the breakpoint stuff also works as software event */ - case PERF_TYPE_BREAKPOINT: - return 1; - } - return 0; + return event->pmu->task_ctx_nr == perf_sw_context; } extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; @@ -954,18 +1004,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs) perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } -static inline void +static __always_inline void perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { - if (atomic_read(&perf_swevent_enabled[event_id])) { - struct pt_regs hot_regs; - - if (!regs) { - perf_fetch_caller_regs(&hot_regs); - regs = &hot_regs; - } - __perf_sw_event(event_id, nr, nmi, regs, addr); + struct pt_regs hot_regs; + + JUMP_LABEL(&perf_swevent_enabled[event_id], have_event); + return; + +have_event: + if (!regs) { + perf_fetch_caller_regs(&hot_regs); + regs = &hot_regs; } + __perf_sw_event(event_id, nr, nmi, regs, addr); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -976,7 +1028,21 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks extern void perf_event_comm(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); -extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs); +/* Callchains */ +DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); + +extern void perf_callchain_user(struct perf_callchain_entry *entry, + struct pt_regs *regs); +extern void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs); + + +static inline void +perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) +{ + if (entry->nr < PERF_MAX_STACK_DEPTH) + entry->ip[entry->nr++] = ip; +} extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; @@ -1019,21 +1085,18 @@ extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); +extern void perf_event_task_tick(void); #else static inline void perf_event_task_sched_in(struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) { } -static inline void -perf_event_task_tick(struct task_struct *task) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } -static inline void perf_event_do_pending(void) { } +static inline void perf_event_delayed_put(struct task_struct *task) { } static inline void perf_event_print_debug(void) { } -static inline void perf_disable(void) { } -static inline void perf_enable(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } @@ -1056,6 +1119,7 @@ static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } +static inline void perf_event_task_tick(void) { } #endif #define perf_output_put(handle, x) \ diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 634b8e674ac5..a39cbed9ee17 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -47,6 +47,8 @@ static inline void *radix_tree_indirect_to_ptr(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INDIRECT_PTR); } +#define radix_tree_indirect_to_ptr(ptr) \ + radix_tree_indirect_to_ptr((void __force *)(ptr)) static inline int radix_tree_is_indirect_ptr(void *ptr) { @@ -61,7 +63,7 @@ static inline int radix_tree_is_indirect_ptr(void *ptr) struct radix_tree_root { unsigned int height; gfp_t gfp_mask; - struct radix_tree_node *rnode; + struct radix_tree_node __rcu *rnode; }; #define RADIX_TREE_INIT(mask) { \ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 4ec3b38ce9c5..f31ef61f1c65 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -10,6 +10,21 @@ #include <linux/rcupdate.h> /* + * Why is there no list_empty_rcu()? Because list_empty() serves this + * purpose. The list_empty() function fetches the RCU-protected pointer + * and compares it to the address of the list head, but neither dereferences + * this pointer itself nor provides this pointer to the caller. Therefore, + * it is not necessary to use rcu_dereference(), so that list_empty() can + * be used anywhere you would want to use a list_empty_rcu(). + */ + +/* + * return the ->next pointer of a list_head in an rcu safe + * way, we must not access it directly + */ +#define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) + +/* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know @@ -20,7 +35,7 @@ static inline void __list_add_rcu(struct list_head *new, { new->next = next; new->prev = prev; - rcu_assign_pointer(prev->next, new); + rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } @@ -138,7 +153,7 @@ static inline void list_replace_rcu(struct list_head *old, { new->next = old->next; new->prev = old->prev; - rcu_assign_pointer(new->prev->next, new); + rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } @@ -193,7 +208,7 @@ static inline void list_splice_init_rcu(struct list_head *list, */ last->next = at; - rcu_assign_pointer(head->next, first); + rcu_assign_pointer(list_next_rcu(head), first); first->prev = head; at->prev = last; } @@ -208,7 +223,9 @@ static inline void list_splice_init_rcu(struct list_head *list, * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ - container_of(rcu_dereference_raw(ptr), type, member) + ({typeof (*ptr) __rcu *__ptr = (typeof (*ptr) __rcu __force *)ptr; \ + container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \ + }) /** * list_first_entry_rcu - get the first element from a list @@ -225,9 +242,9 @@ static inline void list_splice_init_rcu(struct list_head *list, list_entry_rcu((ptr)->next, type, member) #define __list_for_each_rcu(pos, head) \ - for (pos = rcu_dereference_raw((head)->next); \ + for (pos = rcu_dereference_raw(list_next_rcu(head)); \ pos != (head); \ - pos = rcu_dereference_raw(pos->next)) + pos = rcu_dereference_raw(list_next_rcu((pos))) /** * list_for_each_entry_rcu - iterate over rcu list of given type @@ -257,9 +274,9 @@ static inline void list_splice_init_rcu(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_continue_rcu(pos, head) \ - for ((pos) = rcu_dereference_raw((pos)->next); \ + for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \ prefetch((pos)->next), (pos) != (head); \ - (pos) = rcu_dereference_raw((pos)->next)) + (pos) = rcu_dereference_raw(list_next_rcu(pos))) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type @@ -314,12 +331,19 @@ static inline void hlist_replace_rcu(struct hlist_node *old, new->next = next; new->pprev = old->pprev; - rcu_assign_pointer(*new->pprev, new); + rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) new->next->pprev = &new->next; old->pprev = LIST_POISON2; } +/* + * return the first or the next element in an RCU protected hlist + */ +#define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) +#define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) +#define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) + /** * hlist_add_head_rcu * @n: the element to add to the hash list. @@ -346,7 +370,7 @@ static inline void hlist_add_head_rcu(struct hlist_node *n, n->next = first; n->pprev = &h->first; - rcu_assign_pointer(h->first, n); + rcu_assign_pointer(hlist_first_rcu(h), n); if (first) first->pprev = &n->next; } @@ -374,7 +398,7 @@ static inline void hlist_add_before_rcu(struct hlist_node *n, { n->pprev = next->pprev; n->next = next; - rcu_assign_pointer(*(n->pprev), n); + rcu_assign_pointer(hlist_pprev_rcu(n), n); next->pprev = &n->next; } @@ -401,15 +425,15 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, { n->next = prev->next; n->pprev = &prev->next; - rcu_assign_pointer(prev->next, n); + rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) n->next->pprev = &n->next; } -#define __hlist_for_each_rcu(pos, head) \ - for (pos = rcu_dereference((head)->first); \ - pos && ({ prefetch(pos->next); 1; }); \ - pos = rcu_dereference(pos->next)) +#define __hlist_for_each_rcu(pos, head) \ + for (pos = rcu_dereference(hlist_first_rcu(head)); \ + pos && ({ prefetch(pos->next); 1; }); \ + pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type @@ -422,11 +446,11 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define hlist_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference_raw((head)->first); \ +#define hlist_for_each_entry_rcu(tpos, pos, head, member) \ + for (pos = rcu_dereference_raw(hlist_first_rcu(head)); \ pos && ({ prefetch(pos->next); 1; }) && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_raw(pos->next)) + pos = rcu_dereference_raw(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index b70ffe53cb9f..2ae13714828b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -37,6 +37,12 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) } } +#define hlist_nulls_first_rcu(head) \ + (*((struct hlist_nulls_node __rcu __force **)&(head)->first)) + +#define hlist_nulls_next_rcu(node) \ + (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) + /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. @@ -88,7 +94,7 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, n->next = first; n->pprev = &h->first; - rcu_assign_pointer(h->first, n); + rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) first->pprev = &n->next; } @@ -100,11 +106,11 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, * @member: the name of the hlist_nulls_node within the struct. * */ -#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference_raw((head)->first); \ - (!is_a_nulls(pos)) && \ +#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ + for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ + (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_raw(pos->next)) + pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) #endif #endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 83af1f8d8b74..03cda7bed985 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -41,11 +41,15 @@ #include <linux/lockdep.h> #include <linux/completion.h> #include <linux/debugobjects.h> +#include <linux/compiler.h> #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; /* for sysctl */ #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ +#define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) +#define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) + /** * struct rcu_head - callback structure for use with RCU * @next: next update requests in a list @@ -57,29 +61,94 @@ struct rcu_head { }; /* Exported common interfaces */ -extern void rcu_barrier(void); +extern void call_rcu_sched(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)); +extern void synchronize_sched(void); extern void rcu_barrier_bh(void); extern void rcu_barrier_sched(void); extern void synchronize_sched_expedited(void); extern int sched_expedited_torture_stats(char *page); +static inline void __rcu_read_lock_bh(void) +{ + local_bh_disable(); +} + +static inline void __rcu_read_unlock_bh(void) +{ + local_bh_enable(); +} + +#ifdef CONFIG_PREEMPT_RCU + +extern void __rcu_read_lock(void); +extern void __rcu_read_unlock(void); +void synchronize_rcu(void); + +/* + * Defined as a macro as it is a very low level header included from + * areas that don't even know about current. This gives the rcu_read_lock() + * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other + * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. + */ +#define rcu_preempt_depth() (current->rcu_read_lock_nesting) + +#else /* #ifdef CONFIG_PREEMPT_RCU */ + +static inline void __rcu_read_lock(void) +{ + preempt_disable(); +} + +static inline void __rcu_read_unlock(void) +{ + preempt_enable(); +} + +static inline void synchronize_rcu(void) +{ + synchronize_sched(); +} + +static inline int rcu_preempt_depth(void) +{ + return 0; +} + +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + /* Internal to kernel */ extern void rcu_init(void); +extern void rcu_sched_qs(int cpu); +extern void rcu_bh_qs(int cpu); +extern void rcu_check_callbacks(int cpu, int user); +struct notifier_block; + +#ifdef CONFIG_NO_HZ + +extern void rcu_enter_nohz(void); +extern void rcu_exit_nohz(void); + +#else /* #ifdef CONFIG_NO_HZ */ + +static inline void rcu_enter_nohz(void) +{ +} + +static inline void rcu_exit_nohz(void) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) #include <linux/rcutree.h> -#elif defined(CONFIG_TINY_RCU) +#elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif -#define RCU_HEAD_INIT { .next = NULL, .func = NULL } -#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT -#define INIT_RCU_HEAD(ptr) do { \ - (ptr)->next = NULL; (ptr)->func = NULL; \ -} while (0) - /* * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic * initialization and destruction of rcu_head on the stack. rcu_head structures @@ -120,14 +189,15 @@ extern struct lockdep_map rcu_sched_lock_map; extern int debug_lockdep_rcu_enabled(void); /** - * rcu_read_lock_held - might we be in RCU read-side critical section? + * rcu_read_lock_held() - might we be in RCU read-side critical section? * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an RCU read-side critical section unless it can - * prove otherwise. + * prove otherwise. This is useful for debug checks in functions that + * require that they be called within an RCU read-side critical section. * - * Check debug_lockdep_rcu_enabled() to prevent false positives during boot + * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. */ static inline int rcu_read_lock_held(void) @@ -144,14 +214,16 @@ static inline int rcu_read_lock_held(void) extern int rcu_read_lock_bh_held(void); /** - * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? + * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an * RCU-sched read-side critical section. In absence of * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side * critical section unless it can prove otherwise. Note that disabling * of preemption (including disabling irqs) counts as an RCU-sched - * read-side critical section. + * read-side critical section. This is useful for debug checks in functions + * that required that they be called within an RCU-sched read-side + * critical section. * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. @@ -211,7 +283,11 @@ static inline int rcu_read_lock_sched_held(void) extern int rcu_my_thread_group_empty(void); -#define __do_rcu_dereference_check(c) \ +/** + * rcu_lockdep_assert - emit lockdep splat if specified condition not met + * @c: condition to check + */ +#define rcu_lockdep_assert(c) \ do { \ static bool __warned; \ if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \ @@ -220,41 +296,163 @@ extern int rcu_my_thread_group_empty(void); } \ } while (0) +#else /* #ifdef CONFIG_PROVE_RCU */ + +#define rcu_lockdep_assert(c) do { } while (0) + +#endif /* #else #ifdef CONFIG_PROVE_RCU */ + +/* + * Helper functions for rcu_dereference_check(), rcu_dereference_protected() + * and rcu_assign_pointer(). Some of these could be folded into their + * callers, but they are left separate in order to ease introduction of + * multiple flavors of pointers to match the multiple flavors of RCU + * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in + * the future. + */ + +#ifdef __CHECKER__ +#define rcu_dereference_sparse(p, space) \ + ((void)(((typeof(*p) space *)p) == p)) +#else /* #ifdef __CHECKER__ */ +#define rcu_dereference_sparse(p, space) +#endif /* #else #ifdef __CHECKER__ */ + +#define __rcu_access_pointer(p, space) \ + ({ \ + typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ + rcu_dereference_sparse(p, space); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ + }) +#define __rcu_dereference_check(p, c, space) \ + ({ \ + typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ + rcu_lockdep_assert(c); \ + rcu_dereference_sparse(p, space); \ + smp_read_barrier_depends(); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ + }) +#define __rcu_dereference_protected(p, c, space) \ + ({ \ + rcu_lockdep_assert(c); \ + rcu_dereference_sparse(p, space); \ + ((typeof(*p) __force __kernel *)(p)); \ + }) + +#define __rcu_dereference_index_check(p, c) \ + ({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + rcu_lockdep_assert(c); \ + smp_read_barrier_depends(); \ + (_________p1); \ + }) +#define __rcu_assign_pointer(p, v, space) \ + ({ \ + if (!__builtin_constant_p(v) || \ + ((v) != NULL)) \ + smp_wmb(); \ + (p) = (typeof(*v) __force space *)(v); \ + }) + + +/** + * rcu_access_pointer() - fetch RCU pointer with no dereferencing + * @p: The pointer to read + * + * Return the value of the specified RCU-protected pointer, but omit the + * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful + * when the value of this pointer is accessed, but the pointer is not + * dereferenced, for example, when testing an RCU-protected pointer against + * NULL. Although rcu_access_pointer() may also be used in cases where + * update-side locks prevent the value of the pointer from changing, you + * should instead use rcu_dereference_protected() for this use case. + */ +#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) + /** - * rcu_dereference_check - rcu_dereference with debug checking + * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the - * dereference will take place are correct. Typically the conditions indicate - * the various locking conditions that should be held at that point. The check - * should return true if the conditions are satisfied. + * dereference will take place are correct. Typically the conditions + * indicate the various locking conditions that should be held at that + * point. The check should return true if the conditions are satisfied. + * An implicit check for being in an RCU read-side critical section + * (rcu_read_lock()) is included. * * For example: * - * bar = rcu_dereference_check(foo->bar, rcu_read_lock_held() || - * lockdep_is_held(&foo->lock)); + * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced - * if either the RCU read lock is held, or that the lock required to replace + * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * - * bar = rcu_dereference_check(foo->bar, rcu_read_lock_held() || - * lockdep_is_held(&foo->lock) || + * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); + * + * Inserts memory barriers on architectures that require them + * (currently only the Alpha), prevents the compiler from refetching + * (and from merging fetches), and, more importantly, documents exactly + * which pointers are protected by RCU and checks that the pointer is + * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ - ({ \ - __do_rcu_dereference_check(c); \ - rcu_dereference_raw(p); \ - }) + __rcu_dereference_check((p), rcu_read_lock_held() || (c), __rcu) + +/** + * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * This is the RCU-bh counterpart to rcu_dereference_check(). + */ +#define rcu_dereference_bh_check(p, c) \ + __rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu) /** - * rcu_dereference_protected - fetch RCU pointer when updates prevented + * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * This is the RCU-sched counterpart to rcu_dereference_check(). + */ +#define rcu_dereference_sched_check(p, c) \ + __rcu_dereference_check((p), rcu_read_lock_sched_held() || (c), \ + __rcu) + +#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/ + +/** + * rcu_dereference_index_check() - rcu_dereference for indices with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * Similar to rcu_dereference_check(), but omits the sparse checking. + * This allows rcu_dereference_index_check() to be used on integers, + * which can then be used as array indices. Attempting to use + * rcu_dereference_check() on an integer will give compiler warnings + * because the sparse address-space mechanism relies on dereferencing + * the RCU-protected pointer. Dereferencing integers is not something + * that even gcc will put up with. + * + * Note that this function does not implicitly check for RCU read-side + * critical sections. If this function gains lots of uses, it might + * make sense to provide versions for each flavor of RCU, but it does + * not make sense as of early 2010. + */ +#define rcu_dereference_index_check(p, c) \ + __rcu_dereference_index_check((p), (c)) + +/** + * rcu_dereference_protected() - fetch RCU pointer when updates prevented + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * both the smp_read_barrier_depends() and the ACCESS_ONCE(). This @@ -263,35 +461,61 @@ extern int rcu_my_thread_group_empty(void); * prevent the compiler from repeating this reference or combining it * with other references, so it should not be used without protection * of appropriate locks. + * + * This function is only for update-side use. Using this function + * when protected only by rcu_read_lock() will result in infrequent + * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ - ({ \ - __do_rcu_dereference_check(c); \ - (p); \ - }) + __rcu_dereference_protected((p), (c), __rcu) -#else /* #ifdef CONFIG_PROVE_RCU */ +/** + * rcu_dereference_bh_protected() - fetch RCU-bh pointer when updates prevented + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * This is the RCU-bh counterpart to rcu_dereference_protected(). + */ +#define rcu_dereference_bh_protected(p, c) \ + __rcu_dereference_protected((p), (c), __rcu) -#define rcu_dereference_check(p, c) rcu_dereference_raw(p) -#define rcu_dereference_protected(p, c) (p) +/** + * rcu_dereference_sched_protected() - fetch RCU-sched pointer when updates prevented + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * This is the RCU-sched counterpart to rcu_dereference_protected(). + */ +#define rcu_dereference_sched_protected(p, c) \ + __rcu_dereference_protected((p), (c), __rcu) -#endif /* #else #ifdef CONFIG_PROVE_RCU */ /** - * rcu_access_pointer - fetch RCU pointer with no dereferencing + * rcu_dereference() - fetch RCU-protected pointer for dereferencing + * @p: The pointer to read, prior to dereferencing * - * Return the value of the specified RCU-protected pointer, but omit the - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful - * when the value of this pointer is accessed, but the pointer is not - * dereferenced, for example, when testing an RCU-protected pointer against - * NULL. This may also be used in cases where update-side locks prevent - * the value of the pointer from changing, but rcu_dereference_protected() - * is a lighter-weight primitive for this use case. + * This is a simple wrapper around rcu_dereference_check(). + */ +#define rcu_dereference(p) rcu_dereference_check(p, 0) + +/** + * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing + * @p: The pointer to read, prior to dereferencing + * + * Makes rcu_dereference_check() do the dirty work. + */ +#define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) + +/** + * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing + * @p: The pointer to read, prior to dereferencing + * + * Makes rcu_dereference_check() do the dirty work. */ -#define rcu_access_pointer(p) ACCESS_ONCE(p) +#define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** - * rcu_read_lock - mark the beginning of an RCU read-side critical section. + * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the @@ -302,7 +526,7 @@ extern int rcu_my_thread_group_empty(void); * until after the all the other CPUs exit their critical sections. * * Note, however, that RCU callbacks are permitted to run concurrently - * with RCU read-side critical sections. One way that this can happen + * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, @@ -317,7 +541,20 @@ extern int rcu_my_thread_group_empty(void); * will be deferred until the outermost RCU read-side critical section * completes. * - * It is illegal to block while in an RCU read-side critical section. + * You can avoid reading and understanding the next paragraph by + * following this rule: don't put anything in an rcu_read_lock() RCU + * read-side critical section that would block in a !PREEMPT kernel. + * But if you want the full story, read on! + * + * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it + * is illegal to block while in an RCU read-side critical section. In + * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU) + * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may + * be preempted, but explicit blocking is illegal. Finally, in preemptible + * RCU implementations in real-time (CONFIG_PREEMPT_RT) kernel builds, + * RCU read-side critical sections may be preempted and they may also + * block, but only when acquiring spinlocks that are subject to priority + * inheritance. */ static inline void rcu_read_lock(void) { @@ -337,7 +574,7 @@ static inline void rcu_read_lock(void) */ /** - * rcu_read_unlock - marks the end of an RCU read-side critical section. + * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * See rcu_read_lock() for more information. */ @@ -349,15 +586,16 @@ static inline void rcu_read_unlock(void) } /** - * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section + * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but to be used when updates - * are being done using call_rcu_bh(). Since call_rcu_bh() callbacks - * consider completion of a softirq handler to be a quiescent state, - * a process in RCU read-side critical section must be protected by - * disabling softirqs. Read-side critical sections in interrupt context - * can use just rcu_read_lock(). - * + * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since + * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a + * softirq handler to be a quiescent state, a process in RCU read-side + * critical section must be protected by disabling softirqs. Read-side + * critical sections in interrupt context can use just rcu_read_lock(), + * though this should at least be commented to avoid confusing people + * reading the code. */ static inline void rcu_read_lock_bh(void) { @@ -379,13 +617,12 @@ static inline void rcu_read_unlock_bh(void) } /** - * rcu_read_lock_sched - mark the beginning of a RCU-classic critical section + * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * - * Should be used with either - * - synchronize_sched() - * or - * - call_rcu_sched() and rcu_barrier_sched() - * on the write-side to insure proper synchronization. + * This is equivalent of rcu_read_lock(), but to be used when updates + * are being done using call_rcu_sched() or synchronize_rcu_sched(). + * Read-side critical sections can also be introduced by anything that + * disables preemption, including local_irq_disable() and friends. */ static inline void rcu_read_lock_sched(void) { @@ -420,54 +657,14 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) preempt_enable_notrace(); } - /** - * rcu_dereference_raw - fetch an RCU-protected pointer + * rcu_assign_pointer() - assign to RCU-protected pointer + * @p: pointer to assign to + * @v: value to assign (publish) * - * The caller must be within some flavor of RCU read-side critical - * section, or must be otherwise preventing the pointer from changing, - * for example, by holding an appropriate lock. This pointer may later - * be safely dereferenced. It is the caller's responsibility to have - * done the right thing, as this primitive does no checking of any kind. - * - * Inserts memory barriers on architectures that require them - * (currently only the Alpha), and, more importantly, documents - * exactly which pointers are protected by RCU. - */ -#define rcu_dereference_raw(p) ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - smp_read_barrier_depends(); \ - (_________p1); \ - }) - -/** - * rcu_dereference - fetch an RCU-protected pointer, checking for RCU - * - * Makes rcu_dereference_check() do the dirty work. - */ -#define rcu_dereference(p) \ - rcu_dereference_check(p, rcu_read_lock_held()) - -/** - * rcu_dereference_bh - fetch an RCU-protected pointer, checking for RCU-bh - * - * Makes rcu_dereference_check() do the dirty work. - */ -#define rcu_dereference_bh(p) \ - rcu_dereference_check(p, rcu_read_lock_bh_held() || irqs_disabled()) - -/** - * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched - * - * Makes rcu_dereference_check() do the dirty work. - */ -#define rcu_dereference_sched(p) \ - rcu_dereference_check(p, rcu_read_lock_sched_held()) - -/** - * rcu_assign_pointer - assign (publicize) a pointer to a newly - * initialized structure that will be dereferenced by RCU read-side - * critical sections. Returns the value assigned. + * Assigns the specified value to the specified RCU-protected + * pointer, ensuring that any concurrent RCU readers will see + * any prior initialization. Returns the value assigned. * * Inserts memory barriers on architectures that require them * (pretty much all of them other than x86), and also prevents @@ -476,14 +673,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * call documents which pointers will be dereferenced by RCU read-side * code. */ - #define rcu_assign_pointer(p, v) \ - ({ \ - if (!__builtin_constant_p(v) || \ - ((v) != NULL)) \ - smp_wmb(); \ - (p) = (v); \ - }) + __rcu_assign_pointer((p), (v), __rcu) + +/** + * RCU_INIT_POINTER() - initialize an RCU protected pointer + * + * Initialize an RCU-protected pointer in such a way to avoid RCU-lockdep + * splats. + */ +#define RCU_INIT_POINTER(p, v) \ + p = (typeof(*v) __force __rcu *)(v) /* Infrastructure to implement the synchronize_() primitives. */ @@ -494,26 +694,37 @@ struct rcu_synchronize { extern void wakeme_after_rcu(struct rcu_head *head); +#ifdef CONFIG_PREEMPT_RCU + /** - * call_rcu - Queue an RCU callback for invocation after a grace period. + * call_rcu() - Queue an RCU callback for invocation after a grace period. * @head: structure to be used for queueing the RCU updates. - * @func: actual update function to be invoked after the grace period + * @func: actual callback function to be invoked after the grace period * - * The update function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. RCU read-side critical + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. RCU read-side critical * sections are delimited by rcu_read_lock() and rcu_read_unlock(), * and may be nested. */ extern void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *head)); +#else /* #ifdef CONFIG_PREEMPT_RCU */ + +/* In classic RCU, call_rcu() is just call_rcu_sched(). */ +#define call_rcu call_rcu_sched + +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + /** - * call_rcu_bh - Queue an RCU for invocation after a quicker grace period. + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. * @head: structure to be used for queueing the RCU updates. - * @func: actual update function to be invoked after the grace period + * @func: actual callback function to be invoked after the grace period * - * The update function will be invoked some time after a full grace + * The callback function will be invoked some time after a full grace * period elapses, in other words after all currently executing RCU * read-side critical sections have completed. call_rcu_bh() assumes * that the read-side critical sections end on completion of a softirq @@ -566,37 +777,4 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -#ifndef CONFIG_PROVE_RCU -#define __do_rcu_dereference_check(c) do { } while (0) -#endif /* #ifdef CONFIG_PROVE_RCU */ - -#define __rcu_dereference_index_check(p, c) \ - ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - __do_rcu_dereference_check(c); \ - smp_read_barrier_depends(); \ - (_________p1); \ - }) - -/** - * rcu_dereference_index_check() - rcu_dereference for indices with debug checking - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * Similar to rcu_dereference_check(), but omits the sparse checking. - * This allows rcu_dereference_index_check() to be used on integers, - * which can then be used as array indices. Attempting to use - * rcu_dereference_check() on an integer will give compiler warnings - * because the sparse address-space mechanism relies on dereferencing - * the RCU-protected pointer. Dereferencing integers is not something - * that even gcc will put up with. - * - * Note that this function does not implicitly check for RCU read-side - * critical sections. If this function gains lots of uses, it might - * make sense to provide versions for each flavor of RCU, but it does - * not make sense as of early 2010. - */ -#define rcu_dereference_index_check(p, c) \ - __rcu_dereference_index_check((p), (c)) - #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index e2e893144a84..13877cb93a60 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,103 +27,101 @@ #include <linux/cache.h> -void rcu_sched_qs(int cpu); -void rcu_bh_qs(int cpu); -static inline void rcu_note_context_switch(int cpu) -{ - rcu_sched_qs(cpu); -} +#define rcu_init_sched() do { } while (0) -#define __rcu_read_lock() preempt_disable() -#define __rcu_read_unlock() preempt_enable() -#define __rcu_read_lock_bh() local_bh_disable() -#define __rcu_read_unlock_bh() local_bh_enable() -#define call_rcu_sched call_rcu +#ifdef CONFIG_TINY_RCU -#define rcu_init_sched() do { } while (0) -extern void rcu_check_callbacks(int cpu, int user); +static inline void synchronize_rcu_expedited(void) +{ + synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */ +} -static inline int rcu_needs_cpu(int cpu) +static inline void rcu_barrier(void) { - return 0; + rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */ } -/* - * Return the number of grace periods. - */ -static inline long rcu_batches_completed(void) +#else /* #ifdef CONFIG_TINY_RCU */ + +void rcu_barrier(void); +void synchronize_rcu_expedited(void); + +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +static inline void synchronize_rcu_bh(void) { - return 0; + synchronize_sched(); } -/* - * Return the number of bottom-half grace periods. - */ -static inline long rcu_batches_completed_bh(void) +static inline void synchronize_rcu_bh_expedited(void) { - return 0; + synchronize_sched(); } -static inline void rcu_force_quiescent_state(void) +#ifdef CONFIG_TINY_RCU + +static inline void rcu_preempt_note_context_switch(void) { } -static inline void rcu_bh_force_quiescent_state(void) +static inline void exit_rcu(void) { } -static inline void rcu_sched_force_quiescent_state(void) +static inline int rcu_needs_cpu(int cpu) { + return 0; } -extern void synchronize_sched(void); +#else /* #ifdef CONFIG_TINY_RCU */ + +void rcu_preempt_note_context_switch(void); +extern void exit_rcu(void); +int rcu_preempt_needs_cpu(void); -static inline void synchronize_rcu(void) +static inline int rcu_needs_cpu(int cpu) { - synchronize_sched(); + return rcu_preempt_needs_cpu(); } -static inline void synchronize_rcu_bh(void) +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +static inline void rcu_note_context_switch(int cpu) { - synchronize_sched(); + rcu_sched_qs(cpu); + rcu_preempt_note_context_switch(); } -static inline void synchronize_rcu_expedited(void) +/* + * Return the number of grace periods. + */ +static inline long rcu_batches_completed(void) { - synchronize_sched(); + return 0; } -static inline void synchronize_rcu_bh_expedited(void) +/* + * Return the number of bottom-half grace periods. + */ +static inline long rcu_batches_completed_bh(void) { - synchronize_sched(); + return 0; } -struct notifier_block; - -#ifdef CONFIG_NO_HZ - -extern void rcu_enter_nohz(void); -extern void rcu_exit_nohz(void); - -#else /* #ifdef CONFIG_NO_HZ */ - -static inline void rcu_enter_nohz(void) +static inline void rcu_force_quiescent_state(void) { } -static inline void rcu_exit_nohz(void) +static inline void rcu_bh_force_quiescent_state(void) { } -#endif /* #else #ifdef CONFIG_NO_HZ */ - -static inline void exit_rcu(void) +static inline void rcu_sched_force_quiescent_state(void) { } -static inline int rcu_preempt_depth(void) +static inline void rcu_cpu_stall_reset(void) { - return 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index c0ed1c056f29..95518e628794 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,64 +30,23 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H -struct notifier_block; - -extern void rcu_sched_qs(int cpu); -extern void rcu_bh_qs(int cpu); extern void rcu_note_context_switch(int cpu); extern int rcu_needs_cpu(int cpu); +extern void rcu_cpu_stall_reset(void); #ifdef CONFIG_TREE_PREEMPT_RCU -extern void __rcu_read_lock(void); -extern void __rcu_read_unlock(void); -extern void synchronize_rcu(void); extern void exit_rcu(void); -/* - * Defined as macro as it is a very low level header - * included from areas that don't even know about current - */ -#define rcu_preempt_depth() (current->rcu_read_lock_nesting) - #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -static inline void __rcu_read_lock(void) -{ - preempt_disable(); -} - -static inline void __rcu_read_unlock(void) -{ - preempt_enable(); -} - -#define synchronize_rcu synchronize_sched - static inline void exit_rcu(void) { } -static inline int rcu_preempt_depth(void) -{ - return 0; -} - #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ -static inline void __rcu_read_lock_bh(void) -{ - local_bh_disable(); -} -static inline void __rcu_read_unlock_bh(void) -{ - local_bh_enable(); -} - -extern void call_rcu_sched(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)); extern void synchronize_rcu_bh(void); -extern void synchronize_sched(void); extern void synchronize_rcu_expedited(void); static inline void synchronize_rcu_bh_expedited(void) @@ -95,7 +54,7 @@ static inline void synchronize_rcu_bh_expedited(void) synchronize_sched_expedited(); } -extern void rcu_check_callbacks(int cpu, int user); +extern void rcu_barrier(void); extern long rcu_batches_completed(void); extern long rcu_batches_completed_bh(void); @@ -104,18 +63,6 @@ extern void rcu_force_quiescent_state(void); extern void rcu_bh_force_quiescent_state(void); extern void rcu_sched_force_quiescent_state(void); -#ifdef CONFIG_NO_HZ -void rcu_enter_nohz(void); -void rcu_exit_nohz(void); -#else /* CONFIG_NO_HZ */ -static inline void rcu_enter_nohz(void) -{ -} -static inline void rcu_exit_nohz(void) -{ -} -#endif /* CONFIG_NO_HZ */ - /* A context switch is a grace period for RCU-sched and RCU-bh. */ static inline int rcu_blocking_is_gp(void) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 1e2a6db2d7dd..0383601a927c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -875,6 +875,7 @@ enum sched_domain_level { SD_LV_NONE = 0, SD_LV_SIBLING, SD_LV_MC, + SD_LV_BOOK, SD_LV_CPU, SD_LV_NODE, SD_LV_ALLNODES, @@ -1160,6 +1161,13 @@ struct sched_rt_entity { struct rcu_node; +enum perf_event_task_context { + perf_invalid_context = -1, + perf_hw_context = 0, + perf_sw_context, + perf_nr_task_contexts, +}; + struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; @@ -1202,11 +1210,13 @@ struct task_struct { unsigned int policy; cpumask_t cpus_allowed; -#ifdef CONFIG_TREE_PREEMPT_RCU +#ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; char rcu_read_unlock_special; - struct rcu_node *rcu_blocked_node; struct list_head rcu_node_entry; +#endif /* #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_TREE_PREEMPT_RCU + struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) @@ -1288,9 +1298,9 @@ struct task_struct { struct list_head cpu_timers[3]; /* process credentials */ - const struct cred *real_cred; /* objective and real subjective task + const struct cred __rcu *real_cred; /* objective and real subjective task * credentials (COW) */ - const struct cred *cred; /* effective (overridable) subjective task + const struct cred __rcu *cred; /* effective (overridable) subjective task * credentials (COW) */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations @@ -1418,7 +1428,7 @@ struct task_struct { #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock */ - struct css_set *cgroups; + struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock */ struct list_head cg_list; #endif @@ -1431,7 +1441,7 @@ struct task_struct { struct futex_pi_state *pi_state_cache; #endif #ifdef CONFIG_PERF_EVENTS - struct perf_event_context *perf_event_ctxp; + struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif @@ -1681,8 +1691,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * /* * Per process flags */ -#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */ - /* Not implemented yet, only for 486*/ +#define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */ #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ @@ -1740,7 +1749,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -#ifdef CONFIG_TREE_PREEMPT_RCU +#ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ #define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ @@ -1749,7 +1758,9 @@ static inline void rcu_copy_process(struct task_struct *p) { p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special = 0; +#ifdef CONFIG_TREE_PREEMPT_RCU p->rcu_blocked_node = NULL; +#endif INIT_LIST_HEAD(&p->rcu_node_entry); } @@ -1826,6 +1837,19 @@ extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * An i/f to runtime opt-in for irq time accounting based off of sched_clock. + * The reason for this explicit opt-in is not to have perf penalty with + * slow sched_clocks. + */ +extern void enable_sched_clock_irqtime(void); +extern void disable_sched_clock_irqtime(void); +#else +static inline void enable_sched_clock_irqtime(void) {} +static inline void disable_sched_clock_irqtime(void) {} +#endif + extern unsigned long long task_sched_runtime(struct task_struct *task); extern unsigned long long thread_group_sched_runtime(struct task_struct *task); @@ -2367,9 +2391,9 @@ extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_softirq(void); -#define cond_resched_softirq() ({ \ - __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \ - __cond_resched_softirq(); \ +#define cond_resched_softirq() ({ \ + __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ }) /* diff --git a/include/linux/security.h b/include/linux/security.h index a22219afff09..b8246a8df7d2 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -74,7 +74,7 @@ extern int cap_file_mmap(struct file *file, unsigned long reqprot, extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); -extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp); +extern int cap_task_setscheduler(struct task_struct *p); extern int cap_task_setioprio(struct task_struct *p, int ioprio); extern int cap_task_setnice(struct task_struct *p, int nice); extern int cap_syslog(int type, bool from_file); @@ -959,6 +959,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * Sets the new child socket's sid to the openreq sid. * @inet_conn_established: * Sets the connection's peersid to the secmark on skb. + * @secmark_relabel_packet: + * check if the process should be allowed to relabel packets to the given secid + * @security_secmark_refcount_inc + * tells the LSM to increment the number of secmark labeling rules loaded + * @security_secmark_refcount_dec + * tells the LSM to decrement the number of secmark labeling rules loaded * @req_classify_flow: * Sets the flow's sid to the openreq sid. * @tun_dev_create: @@ -1279,9 +1285,13 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * Return 0 if permission is granted. * * @secid_to_secctx: - * Convert secid to security context. + * Convert secid to security context. If secdata is NULL the length of + * the result will be returned in seclen, but no secdata will be returned. + * This does mean that the length could change between calls to check the + * length and the next call which actually allocates and returns the secdata. * @secid contains the security ID. * @secdata contains the pointer that stores the converted security context. + * @seclen pointer which contains the length of the data * @secctx_to_secid: * Convert security context to secid. * @secid contains the pointer to the generated security ID. @@ -1501,8 +1511,7 @@ struct security_operations { int (*task_getioprio) (struct task_struct *p); int (*task_setrlimit) (struct task_struct *p, unsigned int resource, struct rlimit *new_rlim); - int (*task_setscheduler) (struct task_struct *p, int policy, - struct sched_param *lp); + int (*task_setscheduler) (struct task_struct *p); int (*task_getscheduler) (struct task_struct *p); int (*task_movememory) (struct task_struct *p); int (*task_kill) (struct task_struct *p, @@ -1594,6 +1603,9 @@ struct security_operations { struct request_sock *req); void (*inet_csk_clone) (struct sock *newsk, const struct request_sock *req); void (*inet_conn_established) (struct sock *sk, struct sk_buff *skb); + int (*secmark_relabel_packet) (u32 secid); + void (*secmark_refcount_inc) (void); + void (*secmark_refcount_dec) (void); void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl); int (*tun_dev_create)(void); void (*tun_dev_post_create)(struct sock *sk); @@ -1752,8 +1764,7 @@ int security_task_setioprio(struct task_struct *p, int ioprio); int security_task_getioprio(struct task_struct *p); int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim); -int security_task_setscheduler(struct task_struct *p, - int policy, struct sched_param *lp); +int security_task_setscheduler(struct task_struct *p); int security_task_getscheduler(struct task_struct *p); int security_task_movememory(struct task_struct *p); int security_task_kill(struct task_struct *p, struct siginfo *info, @@ -2320,11 +2331,9 @@ static inline int security_task_setrlimit(struct task_struct *p, return 0; } -static inline int security_task_setscheduler(struct task_struct *p, - int policy, - struct sched_param *lp) +static inline int security_task_setscheduler(struct task_struct *p) { - return cap_task_setscheduler(p, policy, lp); + return cap_task_setscheduler(p); } static inline int security_task_getscheduler(struct task_struct *p) @@ -2551,6 +2560,9 @@ void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req); void security_inet_conn_established(struct sock *sk, struct sk_buff *skb); +int security_secmark_relabel_packet(u32 secid); +void security_secmark_refcount_inc(void); +void security_secmark_refcount_dec(void); int security_tun_dev_create(void); void security_tun_dev_post_create(struct sock *sk); int security_tun_dev_attach(struct sock *sk); @@ -2705,6 +2717,19 @@ static inline void security_inet_conn_established(struct sock *sk, { } +static inline int security_secmark_relabel_packet(u32 secid) +{ + return 0; +} + +static inline void security_secmark_refcount_inc(void) +{ +} + +static inline void security_secmark_refcount_dec(void) +{ +} + static inline int security_tun_dev_create(void) { return 0; diff --git a/include/linux/selinux.h b/include/linux/selinux.h index 82e0f26a1299..44f459612690 100644 --- a/include/linux/selinux.h +++ b/include/linux/selinux.h @@ -21,74 +21,11 @@ struct kern_ipc_perm; #ifdef CONFIG_SECURITY_SELINUX /** - * selinux_string_to_sid - map a security context string to a security ID - * @str: the security context string to be mapped - * @sid: ID value returned via this. - * - * Returns 0 if successful, with the SID stored in sid. A value - * of zero for sid indicates no SID could be determined (but no error - * occurred). - */ -int selinux_string_to_sid(char *str, u32 *sid); - -/** - * selinux_secmark_relabel_packet_permission - secmark permission check - * @sid: SECMARK ID value to be applied to network packet - * - * Returns 0 if the current task is allowed to set the SECMARK label of - * packets with the supplied security ID. Note that it is implicit that - * the packet is always being relabeled from the default unlabeled value, - * and that the access control decision is made in the AVC. - */ -int selinux_secmark_relabel_packet_permission(u32 sid); - -/** - * selinux_secmark_refcount_inc - increments the secmark use counter - * - * SELinux keeps track of the current SECMARK targets in use so it knows - * when to apply SECMARK label access checks to network packets. This - * function incements this reference count to indicate that a new SECMARK - * target has been configured. - */ -void selinux_secmark_refcount_inc(void); - -/** - * selinux_secmark_refcount_dec - decrements the secmark use counter - * - * SELinux keeps track of the current SECMARK targets in use so it knows - * when to apply SECMARK label access checks to network packets. This - * function decements this reference count to indicate that one of the - * existing SECMARK targets has been removed/flushed. - */ -void selinux_secmark_refcount_dec(void); - -/** * selinux_is_enabled - is SELinux enabled? */ bool selinux_is_enabled(void); #else -static inline int selinux_string_to_sid(const char *str, u32 *sid) -{ - *sid = 0; - return 0; -} - -static inline int selinux_secmark_relabel_packet_permission(u32 sid) -{ - return 0; -} - -static inline void selinux_secmark_refcount_inc(void) -{ - return; -} - -static inline void selinux_secmark_refcount_dec(void) -{ - return; -} - static inline bool selinux_is_enabled(void) { return false; diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4d5d2f546dbf..58971e891f48 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -108,19 +108,43 @@ static inline int srcu_read_lock_held(struct srcu_struct *sp) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** - * srcu_dereference - fetch SRCU-protected pointer with checking + * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing + * @p: the pointer to fetch and protect for later dereferencing + * @sp: pointer to the srcu_struct, which is used to check that we + * really are in an SRCU read-side critical section. + * @c: condition to check for update-side use * - * Makes rcu_dereference_check() do the dirty work. + * If PROVE_RCU is enabled, invoking this outside of an RCU read-side + * critical section will result in an RCU-lockdep splat, unless @c evaluates + * to 1. The @c argument will normally be a logical expression containing + * lockdep_is_held() calls. */ -#define srcu_dereference(p, sp) \ - rcu_dereference_check(p, srcu_read_lock_held(sp)) +#define srcu_dereference_check(p, sp, c) \ + __rcu_dereference_check((p), srcu_read_lock_held(sp) || (c), __rcu) + +/** + * srcu_dereference - fetch SRCU-protected pointer for later dereferencing + * @p: the pointer to fetch and protect for later dereferencing + * @sp: pointer to the srcu_struct, which is used to check that we + * really are in an SRCU read-side critical section. + * + * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU + * is enabled, invoking this outside of an RCU read-side critical + * section will result in an RCU-lockdep splat. + */ +#define srcu_dereference(p, sp) srcu_dereference_check((p), (sp), 0) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @sp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side - * critical sections may be nested. + * critical sections may be nested. However, it is illegal to + * call anything that waits on an SRCU grace period for the same + * srcu_struct, whether directly or indirectly. Please note that + * one way to indirectly wait on an SRCU grace period is to acquire + * a mutex that is held elsewhere while calling synchronize_srcu() or + * synchronize_srcu_expedited(). */ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) { diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 6b524a0d02e4..1808960c5059 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -126,8 +126,8 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); #else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ -static inline int stop_machine(int (*fn)(void *), void *data, - const struct cpumask *cpus) +static inline int __stop_machine(int (*fn)(void *), void *data, + const struct cpumask *cpus) { int ret; local_irq_disable(); @@ -136,5 +136,11 @@ static inline int stop_machine(int (*fn)(void *), void *data, return ret; } +static inline int stop_machine(int (*fn)(void *), void *data, + const struct cpumask *cpus) +{ + return __stop_machine(fn, data, cpus); +} + #endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 671538d25bc1..8eee9dbbfe7a 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -69,7 +69,7 @@ struct gss_cl_ctx { enum rpc_gss_proc gc_proc; u32 gc_seq; spinlock_t gc_seq_lock; - struct gss_ctx *gc_gss_ctx; + struct gss_ctx __rcu *gc_gss_ctx; struct xdr_netobj gc_wire_ctx; u32 gc_win; unsigned long gc_expiry; @@ -80,7 +80,7 @@ struct gss_upcall_msg; struct gss_cred { struct rpc_cred gc_base; enum rpc_gss_svc gc_service; - struct gss_cl_ctx *gc_ctx; + struct gss_cl_ctx __rcu *gc_ctx; struct gss_upcall_msg *gc_upcall; unsigned long gc_upcall_timestamp; unsigned char gc_machine_cred : 1; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index a8cc4e13434c..c90696544176 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -23,12 +23,12 @@ struct restart_block { }; /* For futex_wait and futex_wait_requeue_pi */ struct { - u32 *uaddr; + u32 __user *uaddr; u32 val; u32 flags; u32 bitset; u64 time; - u32 *uaddr2; + u32 __user *uaddr2; } futex; /* For nanosleep */ struct { diff --git a/include/linux/topology.h b/include/linux/topology.h index 64e084ff5e5c..b91a40e847d2 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -201,6 +201,12 @@ int arch_update_cpu_topology(void); .balance_interval = 64, \ } +#ifdef CONFIG_SCHED_BOOK +#ifndef SD_BOOK_INIT +#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!! +#endif +#endif /* CONFIG_SCHED_BOOK */ + #ifdef CONFIG_NUMA #ifndef SD_NODE_INIT #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 103d1b61aacb..a4a90b6726ce 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -17,6 +17,7 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/rcupdate.h> +#include <linux/jump_label.h> struct module; struct tracepoint; @@ -145,7 +146,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ - if (unlikely(__tracepoint_##name.state)) \ + JUMP_LABEL(&__tracepoint_##name.state, do_trace); \ + return; \ +do_trace: \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args)); \ diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index ef6c24a529e1..a4dc5b027bd9 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -51,7 +51,8 @@ static inline u32 task_cls_classid(struct task_struct *p) return 0; rcu_read_lock(); - id = rcu_dereference(net_cls_subsys_id); + id = rcu_dereference_index_check(net_cls_subsys_id, + rcu_read_lock_held()); if (id >= 0) classid = container_of(task_subsys_state(p, id), struct cgroup_cls_state, css)->classid; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index e624dae54fa4..caf17db87dbc 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -75,7 +75,7 @@ struct nf_conntrack_helper; /* nf_conn feature for connections that have a helper */ struct nf_conn_help { /* Helper. if any */ - struct nf_conntrack_helper *helper; + struct nf_conntrack_helper __rcu *helper; union nf_conntrack_help help; diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h index 0e4cfb694fe7..6fa7cbab7d93 100644 --- a/include/trace/events/irq.h +++ b/include/trace/events/irq.h @@ -5,7 +5,9 @@ #define _TRACE_IRQ_H #include <linux/tracepoint.h> -#include <linux/interrupt.h> + +struct irqaction; +struct softirq_action; #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq } #define show_softirq_name(val) \ @@ -93,7 +95,10 @@ DECLARE_EVENT_CLASS(softirq, ), TP_fast_assign( - __entry->vec = (int)(h - vec); + if (vec) + __entry->vec = (int)(h - vec); + else + __entry->vec = (int)(long)h; ), TP_printk("vec=%d [action=%s]", __entry->vec, @@ -136,6 +141,23 @@ DEFINE_EVENT(softirq, softirq_exit, TP_ARGS(h, vec) ); +/** + * softirq_raise - called immediately when a softirq is raised + * @h: pointer to struct softirq_action + * @vec: pointer to first struct softirq_action in softirq_vec array + * + * The @h parameter contains a pointer to the softirq vector number which is + * raised. @vec is NULL and it means @h includes vector number not + * softirq_action. When used in combination with the softirq_entry tracepoint + * we can determine the softirq raise latency. + */ +DEFINE_EVENT(softirq, softirq_raise, + + TP_PROTO(struct softirq_action *h, struct softirq_action *vec), + + TP_ARGS(h, vec) +); + #endif /* _TRACE_IRQ_H */ /* This part must be outside protection */ diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index 188deca2f3c7..8fe1e93f531d 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -6,10 +6,31 @@ #include <linux/netdevice.h> #include <linux/tracepoint.h> +#include <linux/ftrace.h> + +#define NO_DEV "(no_device)" + +TRACE_EVENT(napi_poll, -DECLARE_TRACE(napi_poll, TP_PROTO(struct napi_struct *napi), - TP_ARGS(napi)); + + TP_ARGS(napi), + + TP_STRUCT__entry( + __field( struct napi_struct *, napi) + __string( dev_name, napi->dev ? napi->dev->name : NO_DEV) + ), + + TP_fast_assign( + __entry->napi = napi; + __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); + ), + + TP_printk("napi poll on napi struct %p for device %s", + __entry->napi, __get_str(dev_name)) +); + +#undef NO_DEV #endif /* _TRACE_NAPI_H_ */ diff --git a/include/trace/events/net.h b/include/trace/events/net.h new file mode 100644 index 000000000000..5f247f5ffc56 --- /dev/null +++ b/include/trace/events/net.h @@ -0,0 +1,82 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM net + +#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NET_H + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/ip.h> +#include <linux/tracepoint.h> + +TRACE_EVENT(net_dev_xmit, + + TP_PROTO(struct sk_buff *skb, + int rc), + + TP_ARGS(skb, rc), + + TP_STRUCT__entry( + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( int, rc ) + __string( name, skb->dev->name ) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->rc = rc; + __assign_str(name, skb->dev->name); + ), + + TP_printk("dev=%s skbaddr=%p len=%u rc=%d", + __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) +); + +DECLARE_EVENT_CLASS(net_dev_template, + + TP_PROTO(struct sk_buff *skb), + + TP_ARGS(skb), + + TP_STRUCT__entry( + __field( void *, skbaddr ) + __field( unsigned int, len ) + __string( name, skb->dev->name ) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + __entry->len = skb->len; + __assign_str(name, skb->dev->name); + ), + + TP_printk("dev=%s skbaddr=%p len=%u", + __get_str(name), __entry->skbaddr, __entry->len) +) + +DEFINE_EVENT(net_dev_template, net_dev_queue, + + TP_PROTO(struct sk_buff *skb), + + TP_ARGS(skb) +); + +DEFINE_EVENT(net_dev_template, netif_receive_skb, + + TP_PROTO(struct sk_buff *skb), + + TP_ARGS(skb) +); + +DEFINE_EVENT(net_dev_template, netif_rx, + + TP_PROTO(struct sk_buff *skb), + + TP_ARGS(skb) +); +#endif /* _TRACE_NET_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 35a2a6e7bf1e..286784d69b8f 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -10,12 +10,17 @@ #ifndef _TRACE_POWER_ENUM_ #define _TRACE_POWER_ENUM_ enum { - POWER_NONE = 0, - POWER_CSTATE = 1, - POWER_PSTATE = 2, + POWER_NONE = 0, + POWER_CSTATE = 1, /* C-State */ + POWER_PSTATE = 2, /* Fequency change or DVFS */ + POWER_SSTATE = 3, /* Suspend */ }; #endif +/* + * The power events are used for cpuidle & suspend (power_start, power_end) + * and for cpufreq (power_frequency) + */ DECLARE_EVENT_CLASS(power, TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), @@ -70,6 +75,85 @@ TRACE_EVENT(power_end, ); +/* + * The clock events are used for clock enable/disable and for + * clock rate change + */ +DECLARE_EVENT_CLASS(clock, + + TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id), + + TP_ARGS(name, state, cpu_id), + + TP_STRUCT__entry( + __string( name, name ) + __field( u64, state ) + __field( u64, cpu_id ) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->state = state; + __entry->cpu_id = cpu_id; + ), + + TP_printk("%s state=%lu cpu_id=%lu", __get_str(name), + (unsigned long)__entry->state, (unsigned long)__entry->cpu_id) +); + +DEFINE_EVENT(clock, clock_enable, + + TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id), + + TP_ARGS(name, state, cpu_id) +); + +DEFINE_EVENT(clock, clock_disable, + + TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id), + + TP_ARGS(name, state, cpu_id) +); + +DEFINE_EVENT(clock, clock_set_rate, + + TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id), + + TP_ARGS(name, state, cpu_id) +); + +/* + * The power domain events are used for power domains transitions + */ +DECLARE_EVENT_CLASS(power_domain, + + TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id), + + TP_ARGS(name, state, cpu_id), + + TP_STRUCT__entry( + __string( name, name ) + __field( u64, state ) + __field( u64, cpu_id ) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->state = state; + __entry->cpu_id = cpu_id; +), + + TP_printk("%s state=%lu cpu_id=%lu", __get_str(name), + (unsigned long)__entry->state, (unsigned long)__entry->cpu_id) +); + +DEFINE_EVENT(power_domain, power_domain_target, + + TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id), + + TP_ARGS(name, state, cpu_id) +); + #endif /* _TRACE_POWER_H */ /* This part must be outside protection */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 9208c92aeab5..f6334782a593 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -362,6 +362,35 @@ TRACE_EVENT(sched_stat_runtime, (unsigned long long)__entry->vruntime) ); +/* + * Tracepoint for showing priority inheritance modifying a tasks + * priority. + */ +TRACE_EVENT(sched_pi_setprio, + + TP_PROTO(struct task_struct *tsk, int newprio), + + TP_ARGS(tsk, newprio), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, oldprio ) + __field( int, newprio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->oldprio = tsk->prio; + __entry->newprio = newprio; + ), + + TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", + __entry->comm, __entry->pid, + __entry->oldprio, __entry->newprio) +); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 4b2be6dc76f0..75ce9d500d8e 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -35,6 +35,23 @@ TRACE_EVENT(kfree_skb, __entry->skbaddr, __entry->protocol, __entry->location) ); +TRACE_EVENT(consume_skb, + + TP_PROTO(struct sk_buff *skb), + + TP_ARGS(skb), + + TP_STRUCT__entry( + __field( void *, skbaddr ) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + ), + + TP_printk("skbaddr=%p", __entry->skbaddr) +); + TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), |