[Drbd-dev] [PATCH 06/16] drbd: user space interface (based upon connector/netlink)
Philipp Reisner
philipp.reisner at linbit.com
Mon Jul 6 17:39:25 CEST 2009
The packets are composed of extensible tag lists. That interface can be
extended over time without breaking old userspace programs.
The nice part of the interface to userspace: drbd.h. The ugly part is for
sure drbd_tag_magic.h..
I realize that macros are generally frowned upon, but this way it is easier
to maintain. The code that gets generated by repeatedly including drbd_nl.h
is hard to maintain over time if it is open coded. (BTW, did you know that
the samba 4 people are proud to have more than 50% of their code auto
generated:)
Signed-off-by: Philipp Reisner <philipp.reisner at linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg at linbit.com>
---
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
new file mode 100644
index 0000000..8f1e2b3
--- /dev/null
+++ b/include/linux/drbd.h
@@ -0,0 +1,349 @@
+/*
+ drbd.h
+ Kernel module for 2.6.x Kernels
+
+ This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+ Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
+ Copyright (C) 2001-2008, Philipp Reisner <philipp.reisner at linbit.com>.
+ Copyright (C) 2001-2008, Lars Ellenberg <lars.ellenberg at linbit.com>.
+
+ drbd is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2, or (at your option)
+ any later version.
+
+ drbd is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with drbd; see the file COPYING. If not, write to
+ the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+*/
+#ifndef DRBD_H
+#define DRBD_H
+#include <linux/connector.h>
+#include <asm/types.h>
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#else
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <limits.h>
+
+/* Altough the Linux source code makes a difference between
+ generic endianness and the bitfields' endianness, there is no
+ architecture as of Linux-2.6.24-rc4 where the bitfileds' endianness
+ does not match the generic endianness. */
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define __LITTLE_ENDIAN_BITFIELD
+#elif __BYTE_ORDER == __BIG_ENDIAN
+#define __BIG_ENDIAN_BITFIELD
+#else
+# error "sorry, weird endianness on this box"
+#endif
+
+#endif
+
+
+extern const char *drbd_buildtag(void);
+#define REL_VERSION "8.3.2"
+#define API_VERSION 88
+#define PRO_VERSION_MIN 86
+#define PRO_VERSION_MAX 90
+
+
+enum drbd_io_error_p {
+ EP_PASS_ON, /* FIXME should the better be named "Ignore"? */
+ EP_CALL_HELPER,
+ EP_DETACH
+};
+
+enum drbd_fencing_p {
+ FP_DONT_CARE,
+ FP_RESOURCE,
+ FP_STONITH
+};
+
+enum drbd_disconnect_p {
+ DP_RECONNECT,
+ DP_DROP_NET_CONF,
+ DP_FREEZE_IO
+};
+
+enum drbd_after_sb_p {
+ ASB_DISCONNECT,
+ ASB_DISCARD_YOUNGER_PRI,
+ ASB_DISCARD_OLDER_PRI,
+ ASB_DISCARD_ZERO_CHG,
+ ASB_DISCARD_LEAST_CHG,
+ ASB_DISCARD_LOCAL,
+ ASB_DISCARD_REMOTE,
+ ASB_CONSENSUS,
+ ASB_DISCARD_SECONDARY,
+ ASB_CALL_HELPER,
+ ASB_VIOLENTLY
+};
+
+/* KEEP the order, do not delete or insert. Only append. */
+enum drbd_ret_codes {
+ ERR_CODE_BASE = 100,
+ NO_ERROR = 101,
+ ERR_LOCAL_ADDR = 102,
+ ERR_PEER_ADDR = 103,
+ ERR_OPEN_DISK = 104,
+ ERR_OPEN_MD_DISK = 105,
+ ERR_DISK_NOT_BDEV = 107,
+ ERR_MD_NOT_BDEV = 108,
+ ERR_DISK_TO_SMALL = 111,
+ ERR_MD_DISK_TO_SMALL = 112,
+ ERR_BDCLAIM_DISK = 114,
+ ERR_BDCLAIM_MD_DISK = 115,
+ ERR_MD_IDX_INVALID = 116,
+ ERR_IO_MD_DISK = 118,
+ ERR_MD_INVALID = 119,
+ ERR_AUTH_ALG = 120,
+ ERR_AUTH_ALG_ND = 121,
+ ERR_NOMEM = 122,
+ ERR_DISCARD = 123,
+ ERR_DISK_CONFIGURED = 124,
+ ERR_NET_CONFIGURED = 125,
+ ERR_MANDATORY_TAG = 126,
+ ERR_MINOR_INVALID = 127,
+ ERR_INTR = 129, /* EINTR */
+ ERR_RESIZE_RESYNC = 130,
+ ERR_NO_PRIMARY = 131,
+ ERR_SYNC_AFTER = 132,
+ ERR_SYNC_AFTER_CYCLE = 133,
+ ERR_PAUSE_IS_SET = 134,
+ ERR_PAUSE_IS_CLEAR = 135,
+ ERR_PACKET_NR = 137,
+ ERR_NO_DISK = 138,
+ ERR_NOT_PROTO_C = 139,
+ ERR_NOMEM_BITMAP = 140,
+ ERR_INTEGRITY_ALG = 141, /* DRBD 8.2 only */
+ ERR_INTEGRITY_ALG_ND = 142, /* DRBD 8.2 only */
+ ERR_CPU_MASK_PARSE = 143, /* DRBD 8.2 only */
+ ERR_CSUMS_ALG = 144, /* DRBD 8.2 only */
+ ERR_CSUMS_ALG_ND = 145, /* DRBD 8.2 only */
+ ERR_VERIFY_ALG = 146, /* DRBD 8.2 only */
+ ERR_VERIFY_ALG_ND = 147, /* DRBD 8.2 only */
+ ERR_CSUMS_RESYNC_RUNNING= 148, /* DRBD 8.2 only */
+ ERR_VERIFY_RUNNING = 149, /* DRBD 8.2 only */
+ ERR_DATA_NOT_CURRENT = 150,
+ ERR_CONNECTED = 151, /* DRBD 8.3 only */
+
+ /* insert new ones above this line */
+ AFTER_LAST_ERR_CODE
+};
+
+#define DRBD_PROT_A 1
+#define DRBD_PROT_B 2
+#define DRBD_PROT_C 3
+
+enum drbd_role {
+ R_UNKNOWN = 0,
+ R_PRIMARY = 1, /* role */
+ R_SECONDARY = 2, /* role */
+ R_MASK = 3,
+};
+
+/* The order of these constants is important.
+ * The lower ones (<C_WF_REPORT_PARAMS) indicate
+ * that there is no socket!
+ * >=C_WF_REPORT_PARAMS ==> There is a socket
+ */
+enum drbd_conns {
+ C_STANDALONE,
+ C_DISCONNECTING, /* Temporal state on the way to StandAlone. */
+ C_UNCONNECTED, /* >= C_UNCONNECTED -> inc_net() succeeds */
+
+ /* These temporal states are all used on the way
+ * from >= C_CONNECTED to Unconnected.
+ * The 'disconnect reason' states
+ * I do not allow to change beween them. */
+ C_TIMEOUT,
+ C_BROKEN_PIPE,
+ C_NETWORK_FAILURE,
+ C_PROTOCOL_ERROR,
+ C_TEAR_DOWN,
+
+ C_WF_CONNECTION,
+ C_WF_REPORT_PARAMS, /* we have a socket */
+ C_CONNECTED, /* we have introduced each other */
+ C_STARTING_SYNC_S, /* starting full sync by admin request. */
+ C_STARTING_SYNC_T, /* stariing full sync by admin request. */
+ C_WF_BITMAP_S,
+ C_WF_BITMAP_T,
+ C_WF_SYNC_UUID,
+
+ /* All SyncStates are tested with this comparison
+ * xx >= C_SYNC_SOURCE && xx <= C_PAUSED_SYNC_T */
+ C_SYNC_SOURCE,
+ C_SYNC_TARGET,
+ C_VERIFY_S,
+ C_VERIFY_T,
+ C_PAUSED_SYNC_S,
+ C_PAUSED_SYNC_T,
+ C_MASK = 31
+};
+
+enum drbd_disk_state {
+ D_DISKLESS,
+ D_ATTACHING, /* In the process of reading the meta-data */
+ D_FAILED, /* Becomes D_DISKLESS as soon as we told it the peer */
+ /* when >= D_FAILED it is legal to access mdev->bc */
+ D_NEGOTIATING, /* Late attaching state, we need to talk to the peer */
+ D_INCONSISTENT,
+ D_OUTDATED,
+ D_UNKNOWN, /* Only used for the peer, never for myself */
+ D_CONSISTENT, /* Might be D_OUTDATED, might be D_UP_TO_DATE ... */
+ D_UP_TO_DATE, /* Only this disk state allows applications' IO ! */
+ D_MASK = 15
+};
+
+union drbd_state {
+/* According to gcc's docs is the ...
+ * The order of allocation of bit-fields within a unit (C90 6.5.2.1, C99 6.7.2.1).
+ * Determined by ABI.
+ * pointed out by Maxim Uvarov q<muvarov at ru.mvista.com>
+ * even though we transmit as "cpu_to_be32(state)",
+ * the offsets of the bitfields still need to be swapped
+ * on different endianess.
+ */
+ struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ unsigned role:2 ; /* 3/4 primary/secondary/unknown */
+ unsigned peer:2 ; /* 3/4 primary/secondary/unknown */
+ unsigned conn:5 ; /* 17/32 cstates */
+ unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
+ unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
+ unsigned susp:1 ; /* 2/2 IO suspended no/yes */
+ unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
+ unsigned peer_isp:1 ;
+ unsigned user_isp:1 ;
+ unsigned _pad:11; /* 0 unused */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ unsigned _pad:11; /* 0 unused */
+ unsigned user_isp:1 ;
+ unsigned peer_isp:1 ;
+ unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
+ unsigned susp:1 ; /* 2/2 IO suspended no/yes */
+ unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
+ unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
+ unsigned conn:5 ; /* 17/32 cstates */
+ unsigned peer:2 ; /* 3/4 primary/secondary/unknown */
+ unsigned role:2 ; /* 3/4 primary/secondary/unknown */
+#else
+# error "this endianess is not supported"
+#endif
+ };
+ unsigned int i;
+};
+
+enum drbd_state_ret_codes {
+ SS_CW_NO_NEED = 4,
+ SS_CW_SUCCESS = 3,
+ SS_NOTHING_TO_DO = 2,
+ SS_SUCCESS = 1,
+ SS_UNKNOWN_ERROR = 0, /* Used to sleep longer in _drbd_request_state */
+ SS_TWO_PRIMARIES = -1,
+ SS_NO_UP_TO_DATE_DISK = -2,
+ SS_NO_LOCAL_DISK = -4,
+ SS_NO_REMOTE_DISK = -5,
+ SS_CONNECTED_OUTDATES = -6,
+ SS_PRIMARY_NOP = -7,
+ SS_RESYNC_RUNNING = -8,
+ SS_ALREADY_STANDALONE = -9,
+ SS_CW_FAILED_BY_PEER = -10,
+ SS_IS_DISKLESS = -11,
+ SS_DEVICE_IN_USE = -12,
+ SS_NO_NET_CONFIG = -13,
+ SS_NO_VERIFY_ALG = -14, /* drbd-8.2 only */
+ SS_NEED_CONNECTION = -15, /* drbd-8.2 only */
+ SS_LOWER_THAN_OUTDATED = -16,
+ SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */
+ SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */
+ SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */
+ SS_AFTER_LAST_ERROR = -20, /* Keep this at bottom */
+};
+
+/* from drbd_strings.c */
+extern const char *conns_to_name(enum drbd_conns);
+extern const char *roles_to_name(enum drbd_role);
+extern const char *disks_to_name(enum drbd_disk_state);
+extern const char *set_st_err_name(enum drbd_state_ret_codes);
+
+#define SHARED_SECRET_MAX 64
+
+#define MDF_CONSISTENT (1 << 0)
+#define MDF_PRIMARY_IND (1 << 1)
+#define MDF_CONNECTED_IND (1 << 2)
+#define MDF_FULL_SYNC (1 << 3)
+#define MDF_WAS_UP_TO_DATE (1 << 4)
+#define MDF_PEER_OUT_DATED (1 << 5)
+#define MDF_CRASHED_PRIMARY (1 << 6)
+
+enum drbd_uuid_index {
+ UI_CURRENT,
+ UI_BITMAP,
+ UI_HISTORY_START,
+ UI_HISTORY_END,
+ UI_SIZE, /* nl-packet: number of dirty bits */
+ UI_FLAGS, /* nl-packet: flags */
+ UI_EXTENDED_SIZE /* Everything. */
+};
+
+enum drbd_timeout_flag {
+ UT_DEFAULT = 0,
+ UT_DEGRADED = 1,
+ UT_PEER_OUTDATED = 2,
+};
+
+#define UUID_JUST_CREATED ((__u64)4)
+
+#define DRBD_MAGIC 0x83740267
+#define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC)
+
+/* these are of type "int" */
+#define DRBD_MD_INDEX_INTERNAL -1
+#define DRBD_MD_INDEX_FLEX_EXT -2
+#define DRBD_MD_INDEX_FLEX_INT -3
+
+/* Start of the new netlink/connector stuff */
+
+#define DRBD_NL_CREATE_DEVICE 0x01
+#define DRBD_NL_SET_DEFAULTS 0x02
+
+/* The following line should be moved over to linux/connector.h
+ * when the time comes */
+#ifndef CN_IDX_DRBD
+# define CN_IDX_DRBD 0x4
+/* Ubuntu "intrepid ibex" release defined CN_IDX_DRBD as 0x6 */
+#endif
+#define CN_VAL_DRBD 0x1
+
+/* For searching a vacant cn_idx value */
+#define CN_IDX_STEP 6977
+
+struct drbd_nl_cfg_req {
+ int packet_type;
+ unsigned int drbd_minor;
+ int flags;
+ unsigned short tag_list[];
+};
+
+struct drbd_nl_cfg_reply {
+ int packet_type;
+ unsigned int minor;
+ int ret_code; /* enum ret_code or set_st_err_t */
+ unsigned short tag_list[]; /* only used with get_* calls */
+};
+
+#endif
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
new file mode 100644
index 0000000..9d067ce
--- /dev/null
+++ b/include/linux/drbd_limits.h
@@ -0,0 +1,137 @@
+/*
+ drbd_limits.h
+ This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+*/
+
+/*
+ * Our current limitations.
+ * Some of them are hard limits,
+ * some of them are arbitrary range limits, that make it easier to provide
+ * feedback about nonsense settings for certain configurable values.
+ */
+
+#ifndef DRBD_LIMITS_H
+#define DRBD_LIMITS_H 1
+
+#define DEBUG_RANGE_CHECK 0
+
+#define DRBD_MINOR_COUNT_MIN 1
+#define DRBD_MINOR_COUNT_MAX 255
+
+#define DRBD_DIALOG_REFRESH_MIN 0
+#define DRBD_DIALOG_REFRESH_MAX 600
+
+/* valid port number */
+#define DRBD_PORT_MIN 1
+#define DRBD_PORT_MAX 0xffff
+
+/* startup { */
+ /* if you want more than 3.4 days, disable */
+#define DRBD_WFC_TIMEOUT_MIN 0
+#define DRBD_WFC_TIMEOUT_MAX 300000
+#define DRBD_WFC_TIMEOUT_DEF 0
+
+#define DRBD_DEGR_WFC_TIMEOUT_MIN 0
+#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000
+#define DRBD_DEGR_WFC_TIMEOUT_DEF 0
+
+#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0
+#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000
+#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0
+/* }*/
+
+/* net { */
+ /* timeout, unit centi seconds
+ * more than one minute timeout is not usefull */
+#define DRBD_TIMEOUT_MIN 1
+#define DRBD_TIMEOUT_MAX 600
+#define DRBD_TIMEOUT_DEF 60 /* 6 seconds */
+
+ /* active connection retries when C_WF_CONNECTION */
+#define DRBD_CONNECT_INT_MIN 1
+#define DRBD_CONNECT_INT_MAX 120
+#define DRBD_CONNECT_INT_DEF 10 /* seconds */
+
+ /* keep-alive probes when idle */
+#define DRBD_PING_INT_MIN 1
+#define DRBD_PING_INT_MAX 120
+#define DRBD_PING_INT_DEF 10
+
+ /* timeout for the ping packets.*/
+#define DRBD_PING_TIMEO_MIN 1
+#define DRBD_PING_TIMEO_MAX 100
+#define DRBD_PING_TIMEO_DEF 5
+
+ /* max number of write requests between write barriers */
+#define DRBD_MAX_EPOCH_SIZE_MIN 1
+#define DRBD_MAX_EPOCH_SIZE_MAX 20000
+#define DRBD_MAX_EPOCH_SIZE_DEF 2048
+
+ /* I don't think that a tcp send buffer of more than 10M is usefull */
+#define DRBD_SNDBUF_SIZE_MIN 0
+#define DRBD_SNDBUF_SIZE_MAX (10<<20)
+#define DRBD_SNDBUF_SIZE_DEF (2*65535)
+
+#define DRBD_RCVBUF_SIZE_MIN 0
+#define DRBD_RCVBUF_SIZE_MAX (10<<20)
+#define DRBD_RCVBUF_SIZE_DEF (2*65535)
+
+ /* @4k PageSize -> 128kB - 512MB */
+#define DRBD_MAX_BUFFERS_MIN 32
+#define DRBD_MAX_BUFFERS_MAX 131072
+#define DRBD_MAX_BUFFERS_DEF 2048
+
+ /* @4k PageSize -> 4kB - 512MB */
+#define DRBD_UNPLUG_WATERMARK_MIN 1
+#define DRBD_UNPLUG_WATERMARK_MAX 131072
+#define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16)
+
+ /* 0 is disabled.
+ * 200 should be more than enough even for very short timeouts */
+#define DRBD_KO_COUNT_MIN 0
+#define DRBD_KO_COUNT_MAX 200
+#define DRBD_KO_COUNT_DEF 0
+/* } */
+
+/* syncer { */
+ /* FIXME allow rate to be zero? */
+#define DRBD_RATE_MIN 1
+/* channel bonding 10 GbE, or other hardware */
+#define DRBD_RATE_MAX (4 << 20)
+#define DRBD_RATE_DEF 250 /* kb/second */
+
+ /* less than 7 would hit performance unneccessarily.
+ * 3833 is the largest prime that still does fit
+ * into 64 sectors of activity log */
+#define DRBD_AL_EXTENTS_MIN 7
+#define DRBD_AL_EXTENTS_MAX 3833
+#define DRBD_AL_EXTENTS_DEF 127
+
+#define DRBD_AFTER_MIN -1
+#define DRBD_AFTER_MAX 255
+#define DRBD_AFTER_DEF -1
+
+/* } */
+
+/* drbdsetup XY resize -d Z
+ * you are free to reduce the device size to nothing, if you want to.
+ * the upper limit with 64bit kernel, enough ram and flexible meta data
+ * is 16 TB, currently. */
+/* DRBD_MAX_SECTORS */
+#define DRBD_DISK_SIZE_SECT_MIN 0
+#define DRBD_DISK_SIZE_SECT_MAX (16 * (2LLU << 30))
+#define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */
+
+#define DRBD_ON_IO_ERROR_DEF EP_PASS_ON
+#define DRBD_FENCING_DEF FP_DONT_CARE
+#define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT
+#define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT
+#define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT
+#define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT
+
+#define DRBD_MAX_BIO_BVECS_MIN 0
+#define DRBD_MAX_BIO_BVECS_MAX 128
+#define DRBD_MAX_BIO_BVECS_DEF 0
+
+#undef RANGE
+#endif
diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
new file mode 100644
index 0000000..db5721a
--- /dev/null
+++ b/include/linux/drbd_nl.h
@@ -0,0 +1,137 @@
+/*
+ PAKET( name,
+ TYPE ( pn, pr, member )
+ ...
+ )
+
+ You may never reissue one of the pn arguments
+*/
+
+#if !defined(NL_PACKET) || !defined(NL_STRING) || !defined(NL_INTEGER) || !defined(NL_BIT) || !defined(NL_INT64)
+#error "The macros NL_PACKET, NL_STRING, NL_INTEGER, NL_INT64 and NL_BIT needs to be defined"
+#endif
+
+NL_PACKET(primary, 1,
+ NL_BIT( 1, T_MAY_IGNORE, overwrite_peer)
+)
+
+NL_PACKET(secondary, 2, )
+
+NL_PACKET(disk_conf, 3,
+ NL_INT64( 2, T_MAY_IGNORE, disk_size)
+ NL_STRING( 3, T_MANDATORY, backing_dev, 128)
+ NL_STRING( 4, T_MANDATORY, meta_dev, 128)
+ NL_INTEGER( 5, T_MANDATORY, meta_dev_idx)
+ NL_INTEGER( 6, T_MAY_IGNORE, on_io_error)
+ NL_INTEGER( 7, T_MAY_IGNORE, fencing)
+ NL_BIT( 37, T_MAY_IGNORE, use_bmbv)
+ NL_BIT( 53, T_MAY_IGNORE, no_disk_flush)
+ NL_BIT( 54, T_MAY_IGNORE, no_md_flush)
+ /* 55 max_bio_size was available in 8.2.6rc2 */
+ NL_INTEGER( 56, T_MAY_IGNORE, max_bio_bvecs)
+ NL_BIT( 57, T_MAY_IGNORE, no_disk_barrier)
+ NL_BIT( 58, T_MAY_IGNORE, no_disk_drain)
+)
+
+NL_PACKET(detach, 4, )
+
+NL_PACKET(net_conf, 5,
+ NL_STRING( 8, T_MANDATORY, my_addr, 128)
+ NL_STRING( 9, T_MANDATORY, peer_addr, 128)
+ NL_STRING( 10, T_MAY_IGNORE, shared_secret, SHARED_SECRET_MAX)
+ NL_STRING( 11, T_MAY_IGNORE, cram_hmac_alg, SHARED_SECRET_MAX)
+ NL_STRING( 44, T_MAY_IGNORE, integrity_alg, SHARED_SECRET_MAX)
+ NL_INTEGER( 14, T_MAY_IGNORE, timeout)
+ NL_INTEGER( 15, T_MANDATORY, wire_protocol)
+ NL_INTEGER( 16, T_MAY_IGNORE, try_connect_int)
+ NL_INTEGER( 17, T_MAY_IGNORE, ping_int)
+ NL_INTEGER( 18, T_MAY_IGNORE, max_epoch_size)
+ NL_INTEGER( 19, T_MAY_IGNORE, max_buffers)
+ NL_INTEGER( 20, T_MAY_IGNORE, unplug_watermark)
+ NL_INTEGER( 21, T_MAY_IGNORE, sndbuf_size)
+ NL_INTEGER( 22, T_MAY_IGNORE, ko_count)
+ NL_INTEGER( 24, T_MAY_IGNORE, after_sb_0p)
+ NL_INTEGER( 25, T_MAY_IGNORE, after_sb_1p)
+ NL_INTEGER( 26, T_MAY_IGNORE, after_sb_2p)
+ NL_INTEGER( 39, T_MAY_IGNORE, rr_conflict)
+ NL_INTEGER( 40, T_MAY_IGNORE, ping_timeo)
+ NL_INTEGER( 67, T_MAY_IGNORE, rcvbuf_size)
+ /* 59 addr_family was available in GIT, never released */
+ NL_BIT( 60, T_MANDATORY, mind_af)
+ NL_BIT( 27, T_MAY_IGNORE, want_lose)
+ NL_BIT( 28, T_MAY_IGNORE, two_primaries)
+ NL_BIT( 41, T_MAY_IGNORE, always_asbp)
+ NL_BIT( 61, T_MAY_IGNORE, no_cork)
+ NL_BIT( 62, T_MANDATORY, auto_sndbuf_size)
+)
+
+NL_PACKET(disconnect, 6, )
+
+NL_PACKET(resize, 7,
+ NL_INT64( 29, T_MAY_IGNORE, resize_size)
+)
+
+NL_PACKET(syncer_conf, 8,
+ NL_INTEGER( 30, T_MAY_IGNORE, rate)
+ NL_INTEGER( 31, T_MAY_IGNORE, after)
+ NL_INTEGER( 32, T_MAY_IGNORE, al_extents)
+ NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX)
+ NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32)
+ NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX)
+ NL_BIT( 65, T_MAY_IGNORE, use_rle)
+)
+
+NL_PACKET(invalidate, 9, )
+NL_PACKET(invalidate_peer, 10, )
+NL_PACKET(pause_sync, 11, )
+NL_PACKET(resume_sync, 12, )
+NL_PACKET(suspend_io, 13, )
+NL_PACKET(resume_io, 14, )
+NL_PACKET(outdate, 15, )
+NL_PACKET(get_config, 16, )
+NL_PACKET(get_state, 17,
+ NL_INTEGER( 33, T_MAY_IGNORE, state_i)
+)
+
+NL_PACKET(get_uuids, 18,
+ NL_STRING( 34, T_MAY_IGNORE, uuids, (UI_SIZE*sizeof(__u64)))
+ NL_INTEGER( 35, T_MAY_IGNORE, uuids_flags)
+)
+
+NL_PACKET(get_timeout_flag, 19,
+ NL_BIT( 36, T_MAY_IGNORE, use_degraded)
+)
+
+NL_PACKET(call_helper, 20,
+ NL_STRING( 38, T_MAY_IGNORE, helper, 32)
+)
+
+/* Tag nr 42 already allocated in drbd-8.1 development. */
+
+NL_PACKET(sync_progress, 23,
+ NL_INTEGER( 43, T_MAY_IGNORE, sync_progress)
+)
+
+NL_PACKET(dump_ee, 24,
+ NL_STRING( 45, T_MAY_IGNORE, dump_ee_reason, 32)
+ NL_STRING( 46, T_MAY_IGNORE, seen_digest, SHARED_SECRET_MAX)
+ NL_STRING( 47, T_MAY_IGNORE, calc_digest, SHARED_SECRET_MAX)
+ NL_INT64( 48, T_MAY_IGNORE, ee_sector)
+ NL_INT64( 49, T_MAY_IGNORE, ee_block_id)
+ NL_STRING( 50, T_MAY_IGNORE, ee_data, 32 << 10)
+)
+
+NL_PACKET(start_ov, 25,
+ NL_INT64( 66, T_MAY_IGNORE, start_sector)
+)
+
+NL_PACKET(new_c_uuid, 26,
+ NL_BIT( 63, T_MANDATORY, clear_bm)
+)
+
+#undef NL_PACKET
+#undef NL_INTEGER
+#undef NL_INT64
+#undef NL_BIT
+#undef NL_STRING
+
diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h
new file mode 100644
index 0000000..fcdff84
--- /dev/null
+++ b/include/linux/drbd_tag_magic.h
@@ -0,0 +1,83 @@
+#ifndef DRBD_TAG_MAGIC_H
+#define DRBD_TAG_MAGIC_H
+
+#define TT_END 0
+#define TT_REMOVED 0xE000
+
+/* declare packet_type enums */
+enum packet_types {
+#define NL_PACKET(name, number, fields) P_ ## name = number,
+#define NL_INTEGER(pn, pr, member)
+#define NL_INT64(pn, pr, member)
+#define NL_BIT(pn, pr, member)
+#define NL_STRING(pn, pr, member, len)
+#include "drbd_nl.h"
+ P_nl_after_last_packet,
+};
+
+/* These struct are used to deduce the size of the tag lists: */
+#define NL_PACKET(name, number, fields) \
+ struct name ## _tag_len_struct { fields };
+#define NL_INTEGER(pn, pr, member) \
+ int member; int tag_and_len ## member;
+#define NL_INT64(pn, pr, member) \
+ __u64 member; int tag_and_len ## member;
+#define NL_BIT(pn, pr, member) \
+ unsigned char member:1; int tag_and_len ## member;
+#define NL_STRING(pn, pr, member, len) \
+ unsigned char member[len]; int member ## _len; \
+ int tag_and_len ## member;
+#include "linux/drbd_nl.h"
+
+/* declate tag-list-sizes */
+static const int tag_list_sizes[] = {
+#define NL_PACKET(name, number, fields) 2 fields ,
+#define NL_INTEGER(pn, pr, member) + 4 + 4
+#define NL_INT64(pn, pr, member) + 4 + 8
+#define NL_BIT(pn, pr, member) + 4 + 1
+#define NL_STRING(pn, pr, member, len) + 4 + (len)
+#include "drbd_nl.h"
+};
+
+/* The two highest bits are used for the tag type */
+#define TT_MASK 0xC000
+#define TT_INTEGER 0x0000
+#define TT_INT64 0x4000
+#define TT_BIT 0x8000
+#define TT_STRING 0xC000
+/* The next bit indicates if processing of the tag is mandatory */
+#define T_MANDATORY 0x2000
+#define T_MAY_IGNORE 0x0000
+#define TN_MASK 0x1fff
+/* The remaining 13 bits are used to enumerate the tags */
+
+#define tag_type(T) ((T) & TT_MASK)
+#define tag_number(T) ((T) & TN_MASK)
+
+/* declare tag enums */
+#define NL_PACKET(name, number, fields) fields
+enum drbd_tags {
+#define NL_INTEGER(pn, pr, member) T_ ## member = pn | TT_INTEGER | pr ,
+#define NL_INT64(pn, pr, member) T_ ## member = pn | TT_INT64 | pr ,
+#define NL_BIT(pn, pr, member) T_ ## member = pn | TT_BIT | pr ,
+#define NL_STRING(pn, pr, member, len) T_ ## member = pn | TT_STRING | pr ,
+#include "drbd_nl.h"
+};
+
+struct tag {
+ const char *name;
+ int type_n_flags;
+ int max_len;
+};
+
+/* declare tag names */
+#define NL_PACKET(name, number, fields) fields
+static const struct tag tag_descriptions[] = {
+#define NL_INTEGER(pn, pr, member) [ pn ] = { #member, TT_INTEGER | pr, sizeof(int) },
+#define NL_INT64(pn, pr, member) [ pn ] = { #member, TT_INT64 | pr, sizeof(__u64) },
+#define NL_BIT(pn, pr, member) [ pn ] = { #member, TT_BIT | pr, sizeof(int) },
+#define NL_STRING(pn, pr, member, len) [ pn ] = { #member, TT_STRING | pr, (len) },
+#include "drbd_nl.h"
+};
+
+#endif
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
new file mode 100644
index 0000000..c3d438c
--- /dev/null
+++ b/drivers/block/drbd/drbd_nl.c
@@ -0,0 +1,2350 @@
+/*
+ drbd_nl.c
+
+ This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+ Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
+ Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner at linbit.com>.
+ Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg at linbit.com>.
+
+ drbd is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2, or (at your option)
+ any later version.
+
+ drbd is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with drbd; see the file COPYING. If not, write to
+ the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ */
+
+#include <linux/autoconf.h>
+#include <linux/module.h>
+#include <linux/drbd.h>
+#include <linux/in.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/connector.h>
+#include <linux/blkpg.h>
+#include <linux/cpumask.h>
+#include "drbd_int.h"
+#include "drbd_tracing.h"
+#include "drbd_wrappers.h"
+#include <asm/unaligned.h>
+#include <linux/drbd_tag_magic.h>
+#include <linux/drbd_limits.h>
+
+static unsigned short *tl_add_blob(unsigned short *, enum drbd_tags, const void *, int);
+static unsigned short *tl_add_str(unsigned short *, enum drbd_tags, const char *);
+static unsigned short *tl_add_int(unsigned short *, enum drbd_tags, const void *);
+
+/* see get_sb_bdev and bd_claim */
+static char *drbd_m_holder = "Hands off! this is DRBD's meta data device.";
+
+/* Generate the tag_list to struct functions */
+#define NL_PACKET(name, number, fields) \
+static int name ## _from_tags(struct drbd_conf *mdev, \
+ unsigned short *tags, struct name *arg) __attribute__ ((unused)); \
+static int name ## _from_tags(struct drbd_conf *mdev, \
+ unsigned short *tags, struct name *arg) \
+{ \
+ int tag; \
+ int dlen; \
+ \
+ while ((tag = get_unaligned(tags++)) != TT_END) { \
+ dlen = get_unaligned(tags++); \
+ switch (tag_number(tag)) { \
+ fields \
+ default: \
+ if (tag & T_MANDATORY) { \
+ dev_err(DEV, "Unknown tag: %d\n", tag_number(tag)); \
+ return 0; \
+ } \
+ } \
+ tags = (unsigned short *)((char *)tags + dlen); \
+ } \
+ return 1; \
+}
+#define NL_INTEGER(pn, pr, member) \
+ case pn: /* D_ASSERT( tag_type(tag) == TT_INTEGER ); */ \
+ arg->member = get_unaligned((int *)(tags)); \
+ break;
+#define NL_INT64(pn, pr, member) \
+ case pn: /* D_ASSERT( tag_type(tag) == TT_INT64 ); */ \
+ arg->member = get_unaligned((u64 *)(tags)); \
+ break;
+#define NL_BIT(pn, pr, member) \
+ case pn: /* D_ASSERT( tag_type(tag) == TT_BIT ); */ \
+ arg->member = *(char *)(tags) ? 1 : 0; \
+ break;
+#define NL_STRING(pn, pr, member, len) \
+ case pn: /* D_ASSERT( tag_type(tag) == TT_STRING ); */ \
+ if (dlen > len) { \
+ dev_err(DEV, "arg too long: %s (%u wanted, max len: %u bytes)\n", \
+ #member, dlen, (unsigned int)len); \
+ return 0; \
+ } \
+ arg->member ## _len = dlen; \
+ memcpy(arg->member, tags, min_t(size_t, dlen, len)); \
+ break;
+#include "linux/drbd_nl.h"
+
+/* Generate the struct to tag_list functions */
+#define NL_PACKET(name, number, fields) \
+static unsigned short* \
+name ## _to_tags(struct drbd_conf *mdev, \
+ struct name *arg, unsigned short *tags) __attribute__ ((unused)); \
+static unsigned short* \
+name ## _to_tags(struct drbd_conf *mdev, \
+ struct name *arg, unsigned short *tags) \
+{ \
+ fields \
+ return tags; \
+}
+
+#define NL_INTEGER(pn, pr, member) \
+ put_unaligned(pn | pr | TT_INTEGER, tags++); \
+ put_unaligned(sizeof(int), tags++); \
+ put_unaligned(arg->member, (int *)tags); \
+ tags = (unsigned short *)((char *)tags+sizeof(int));
+#define NL_INT64(pn, pr, member) \
+ put_unaligned(pn | pr | TT_INT64, tags++); \
+ put_unaligned(sizeof(u64), tags++); \
+ put_unaligned(arg->member, (u64 *)tags); \
+ tags = (unsigned short *)((char *)tags+sizeof(u64));
+#define NL_BIT(pn, pr, member) \
+ put_unaligned(pn | pr | TT_BIT, tags++); \
+ put_unaligned(sizeof(char), tags++); \
+ *(char *)tags = arg->member; \
+ tags = (unsigned short *)((char *)tags+sizeof(char));
+#define NL_STRING(pn, pr, member, len) \
+ put_unaligned(pn | pr | TT_STRING, tags++); \
+ put_unaligned(arg->member ## _len, tags++); \
+ memcpy(tags, arg->member, arg->member ## _len); \
+ tags = (unsigned short *)((char *)tags + arg->member ## _len);
+#include "linux/drbd_nl.h"
+
+void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name);
+void drbd_nl_send_reply(struct cn_msg *, int);
+
+int drbd_khelper(struct drbd_conf *mdev, char *cmd)
+{
+ char *envp[] = { "HOME=/",
+ "TERM=linux",
+ "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+ NULL, /* Will be set to address family */
+ NULL, /* Will be set to address */
+ NULL };
+
+ char mb[12], af[20], ad[60], *afs;
+ char *argv[] = {usermode_helper, cmd, mb, NULL };
+ int ret;
+
+ snprintf(mb, 12, "minor-%d", mdev_to_minor(mdev));
+
+ if (get_net_conf(mdev)) {
+ switch (((struct sockaddr *)mdev->net_conf->peer_addr)->sa_family) {
+ case AF_INET6:
+ afs = "ipv6";
+ snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI6",
+ &((struct sockaddr_in6 *)mdev->net_conf->peer_addr)->sin6_addr);
+ break;
+ case AF_INET:
+ afs = "ipv4";
+ snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI4",
+ &((struct sockaddr_in *)mdev->net_conf->peer_addr)->sin_addr);
+ break;
+ default:
+ afs = "ssocks";
+ snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI4",
+ &((struct sockaddr_in *)mdev->net_conf->peer_addr)->sin_addr);
+ }
+ snprintf(af, 20, "DRBD_PEER_AF=%s", afs);
+ envp[3]=af;
+ envp[4]=ad;
+ put_net_conf(mdev);
+ }
+
+ dev_info(DEV, "helper command: %s %s %s\n", usermode_helper, cmd, mb);
+
+ drbd_bcast_ev_helper(mdev, cmd);
+ ret = call_usermodehelper(usermode_helper, argv, envp, 1);
+ if (ret)
+ dev_warn(DEV, "helper command: %s %s %s exit code %u (0x%x)\n",
+ usermode_helper, cmd, mb,
+ (ret >> 8) & 0xff, ret);
+ else
+ dev_info(DEV, "helper command: %s %s %s exit code %u (0x%x)\n",
+ usermode_helper, cmd, mb,
+ (ret >> 8) & 0xff, ret);
+
+ if (ret < 0) /* Ignore any ERRNOs we got. */
+ ret = 0;
+
+ return ret;
+}
+
+enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev)
+{
+ char *ex_to_string;
+ int r;
+ enum drbd_disk_state nps;
+ enum drbd_fencing_p fp;
+
+ D_ASSERT(mdev->state.pdsk == D_UNKNOWN);
+
+ if (get_ldev_if_state(mdev, D_CONSISTENT)) {
+ fp = mdev->ldev->dc.fencing;
+ put_ldev(mdev);
+ } else {
+ dev_warn(DEV, "Not fencing peer, I'm not even Consistent myself.\n");
+ return mdev->state.pdsk;
+ }
+
+ if (fp == FP_STONITH)
+ _drbd_request_state(mdev, NS(susp, 1), CS_WAIT_COMPLETE);
+
+ r = drbd_khelper(mdev, "fence-peer");
+
+ switch ((r>>8) & 0xff) {
+ case 3: /* peer is inconsistent */
+ ex_to_string = "peer is inconsistent or worse";
+ nps = D_INCONSISTENT;
+ break;
+ case 4:
+ ex_to_string = "peer is outdated";
+ nps = D_OUTDATED;
+ break;
+ case 5: /* peer was down, we will(have) create(d) a new UUID anyways... */
+ /* If we would be more strict, we would return D_UNKNOWN here. */
+ ex_to_string = "peer is unreachable, assumed to be dead";
+ nps = D_OUTDATED;
+ break;
+ case 6: /* Peer is primary, voluntarily outdate myself.
+ * This is useful when an unconnected R_SECONDARY is asked to
+ * become R_PRIMARY, but findes the other peer being active. */
+ ex_to_string = "peer is active";
+ dev_warn(DEV, "Peer is primary, outdating myself.\n");
+ nps = D_UNKNOWN;
+ _drbd_request_state(mdev, NS(disk, D_OUTDATED), CS_WAIT_COMPLETE);
+ break;
+ case 7:
+ if (fp != FP_STONITH)
+ dev_err(DEV, "fence-peer() = 7 && fencing != Stonith !!!\n");
+ ex_to_string = "peer was stonithed";
+ nps = D_OUTDATED;
+ break;
+ default:
+ /* The script is broken ... */
+ nps = D_UNKNOWN;
+ dev_err(DEV, "fence-peer helper broken, returned %d\n", (r>>8)&0xff);
+ return nps;
+ }
+
+ dev_info(DEV, "fence-peer helper returned %d (%s)\n",
+ (r>>8) & 0xff, ex_to_string);
+ return nps;
+}
+
+
+int drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
+{
+ const int max_tries = 4;
+ int r = 0;
+ int try = 0;
+ int forced = 0;
+ union drbd_state mask, val;
+ enum drbd_disk_state nps;
+
+ if (new_role == R_PRIMARY)
+ request_ping(mdev); /* Detect a dead peer ASAP */
+
+ mutex_lock(&mdev->state_mutex);
+
+ mask.i = 0; mask.role = R_MASK;
+ val.i = 0; val.role = new_role;
+
+ while (try++ < max_tries) {
+ r = _drbd_request_state(mdev, mask, val, CS_WAIT_COMPLETE);
+
+ /* in case we first succeeded to outdate,
+ * but now suddenly could establish a connection */
+ if (r == SS_CW_FAILED_BY_PEER && mask.pdsk != 0) {
+ val.pdsk = 0;
+ mask.pdsk = 0;
+ continue;
+ }
+
+ if (r == SS_NO_UP_TO_DATE_DISK && force &&
+ (mdev->state.disk == D_INCONSISTENT ||
+ mdev->state.disk == D_OUTDATED)) {
+ mask.disk = D_MASK;
+ val.disk = D_UP_TO_DATE;
+ forced = 1;
+ continue;
+ }
+
+ if (r == SS_NO_UP_TO_DATE_DISK &&
+ mdev->state.disk == D_CONSISTENT) {
+ D_ASSERT(mdev->state.pdsk == D_UNKNOWN);
+ nps = drbd_try_outdate_peer(mdev);
+
+ if (nps == D_OUTDATED) {
+ val.disk = D_UP_TO_DATE;
+ mask.disk = D_MASK;
+ }
+
+ val.pdsk = nps;
+ mask.pdsk = D_MASK;
+
+ continue;
+ }
+
+ if (r == SS_NOTHING_TO_DO)
+ goto fail;
+ if (r == SS_PRIMARY_NOP) {
+ nps = drbd_try_outdate_peer(mdev);
+
+ if (force && nps > D_OUTDATED) {
+ dev_warn(DEV, "Forced into split brain situation!\n");
+ nps = D_OUTDATED;
+ }
+
+ mask.pdsk = D_MASK;
+ val.pdsk = nps;
+
+ continue;
+ }
+ if (r == SS_TWO_PRIMARIES) {
+ /* Maybe the peer is detected as dead very soon...
+ retry at most once more in this case. */
+ __set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout((mdev->net_conf->ping_timeo+1)*HZ/10);
+ if (try < max_tries)
+ try = max_tries - 1;
+ continue;
+ }
+ if (r < SS_SUCCESS) {
+ r = _drbd_request_state(mdev, mask, val,
+ CS_VERBOSE + CS_WAIT_COMPLETE);
+ if (r < SS_SUCCESS)
+ goto fail;
+ }
+ break;
+ }
+
+ if (forced)
+ dev_warn(DEV, "Forced to consider local data as UpToDate!\n");
+
+ /* Wait until nothing is on the fly :) */
+ wait_event(mdev->misc_wait, atomic_read(&mdev->ap_pending_cnt) == 0);
+
+ if (new_role == R_SECONDARY) {
+ set_disk_ro(mdev->vdisk, TRUE);
+ if (get_ldev(mdev)) {
+ mdev->ldev->md.uuid[UI_CURRENT] &= ~(u64)1;
+ put_ldev(mdev);
+ }
+ } else {
+ if (get_net_conf(mdev)) {
+ mdev->net_conf->want_lose = 0;
+ put_net_conf(mdev);
+ }
+ set_disk_ro(mdev->vdisk, FALSE);
+ if (get_ldev(mdev)) {
+ if (((mdev->state.conn < C_CONNECTED ||
+ mdev->state.pdsk <= D_FAILED)
+ && mdev->ldev->md.uuid[UI_BITMAP] == 0) || forced)
+ drbd_uuid_new_current(mdev);
+
+ mdev->ldev->md.uuid[UI_CURRENT] |= (u64)1;
+ put_ldev(mdev);
+ }
+ }
+
+ if ((new_role == R_SECONDARY) && get_ldev(mdev)) {
+ drbd_al_to_on_disk_bm(mdev);
+ put_ldev(mdev);
+ }
+
+ if (mdev->state.conn >= C_WF_REPORT_PARAMS) {
+ /* if this was forced, we should consider sync */
+ if (forced)
+ drbd_send_uuids(mdev);
+ drbd_send_state(mdev);
+ }
+
+ drbd_md_sync(mdev);
+
+ kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
+ fail:
+ mutex_unlock(&mdev->state_mutex);
+ return r;
+}
+
+
+static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ struct primary primary_args;
+
+ memset(&primary_args, 0, sizeof(struct primary));
+ if (!primary_from_tags(mdev, nlp->tag_list, &primary_args)) {
+ reply->ret_code = ERR_MANDATORY_TAG;
+ return 0;
+ }
+
+ reply->ret_code =
+ drbd_set_role(mdev, R_PRIMARY, primary_args.overwrite_peer);
+
+ return 0;
+}
+
+static int drbd_nl_secondary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ reply->ret_code = drbd_set_role(mdev, R_SECONDARY, 0);
+
+ return 0;
+}
+
+/* initializes the md.*_offset members, so we are able to find
+ * the on disk meta data */
+static void drbd_md_set_sector_offsets(struct drbd_conf *mdev,
+ struct drbd_backing_dev *bdev)
+{
+ sector_t md_size_sect = 0;
+ switch (bdev->dc.meta_dev_idx) {
+ default:
+ /* v07 style fixed size indexed meta data */
+ bdev->md.md_size_sect = MD_RESERVED_SECT;
+ bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
+ bdev->md.al_offset = MD_AL_OFFSET;
+ bdev->md.bm_offset = MD_BM_OFFSET;
+ break;
+ case DRBD_MD_INDEX_FLEX_EXT:
+ /* just occupy the full device; unit: sectors */
+ bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev);
+ bdev->md.md_offset = 0;
+ bdev->md.al_offset = MD_AL_OFFSET;
+ bdev->md.bm_offset = MD_BM_OFFSET;
+ break;
+ case DRBD_MD_INDEX_INTERNAL:
+ case DRBD_MD_INDEX_FLEX_INT:
+ bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
+ /* al size is still fixed */
+ bdev->md.al_offset = -MD_AL_MAX_SIZE;
+ /* we need (slightly less than) ~ this much bitmap sectors: */
+ md_size_sect = drbd_get_capacity(bdev->backing_bdev);
+ md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT);
+ md_size_sect = BM_SECT_TO_EXT(md_size_sect);
+ md_size_sect = ALIGN(md_size_sect, 8);
+
+ /* plus the "drbd meta data super block",
+ * and the activity log; */
+ md_size_sect += MD_BM_OFFSET;
+
+ bdev->md.md_size_sect = md_size_sect;
+ /* bitmap offset is adjusted by 'super' block size */
+ bdev->md.bm_offset = -md_size_sect + MD_AL_OFFSET;
+ break;
+ }
+}
+
+char *ppsize(char *buf, unsigned long long size)
+{
+ /* Needs 9 bytes at max. */
+ static char units[] = { 'K', 'M', 'G', 'T', 'P', 'E' };
+ int base = 0;
+ while (size >= 10000) {
+ /* shift + round */
+ size = (size >> 10) + !!(size & (1<<9));
+ base++;
+ }
+ sprintf(buf, "%lu %cB", (long)size, units[base]);
+
+ return buf;
+}
+
+/* there is still a theoretical deadlock when called from receiver
+ * on an D_INCONSISTENT R_PRIMARY:
+ * remote READ does inc_ap_bio, receiver would need to receive answer
+ * packet from remote to dec_ap_bio again.
+ * receiver receive_sizes(), comes here,
+ * waits for ap_bio_cnt == 0. -> deadlock.
+ * but this cannot happen, actually, because:
+ * R_PRIMARY D_INCONSISTENT, and peer's disk is unreachable
+ * (not connected, or bad/no disk on peer):
+ * see drbd_fail_request_early, ap_bio_cnt is zero.
+ * R_PRIMARY D_INCONSISTENT, and C_SYNC_TARGET:
+ * peer may not initiate a resize.
+ */
+void drbd_suspend_io(struct drbd_conf *mdev)
+{
+ set_bit(SUSPEND_IO, &mdev->flags);
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));
+}
+
+void drbd_resume_io(struct drbd_conf *mdev)
+{
+ clear_bit(SUSPEND_IO, &mdev->flags);
+ wake_up(&mdev->misc_wait);
+}
+
+/**
+ * drbd_determin_dev_size() - Sets the right device size obeying all constraints
+ * @mdev: DRBD device.
+ *
+ * Returns 0 on success, negative return values indicate errors.
+ * You should call drbd_md_sync() after calling this function.
+ */
+enum determine_dev_size drbd_determin_dev_size(struct drbd_conf *mdev) __must_hold(local)
+{
+ sector_t prev_first_sect, prev_size; /* previous meta location */
+ sector_t la_size;
+ sector_t size;
+ char ppb[10];
+
+ int md_moved, la_size_changed;
+ enum determine_dev_size rv = unchanged;
+
+ /* race:
+ * application request passes inc_ap_bio,
+ * but then cannot get an AL-reference.
+ * this function later may wait on ap_bio_cnt == 0. -> deadlock.
+ *
+ * to avoid that:
+ * Suspend IO right here.
+ * still lock the act_log to not trigger ASSERTs there.
+ */
+ drbd_suspend_io(mdev);
+
+ /* no wait necessary anymore, actually we could assert that */
+ wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
+
+ prev_first_sect = drbd_md_first_sector(mdev->ldev);
+ prev_size = mdev->ldev->md.md_size_sect;
+ la_size = mdev->ldev->md.la_size_sect;
+
+ /* TODO: should only be some assert here, not (re)init... */
+ drbd_md_set_sector_offsets(mdev, mdev->ldev);
+
+ size = drbd_new_dev_size(mdev, mdev->ldev);
+
+ if (drbd_get_capacity(mdev->this_bdev) != size ||
+ drbd_bm_capacity(mdev) != size) {
+ int err;
+ err = drbd_bm_resize(mdev, size);
+ if (unlikely(err)) {
+ /* currently there is only one error: ENOMEM! */
+ size = drbd_bm_capacity(mdev)>>1;
+ if (size == 0) {
+ dev_err(DEV, "OUT OF MEMORY! "
+ "Could not allocate bitmap!\n");
+ } else {
+ dev_err(DEV, "BM resizing failed. "
+ "Leaving size unchanged at size = %lu KB\n",
+ (unsigned long)size);
+ }
+ rv = dev_size_error;
+ }
+ /* racy, see comments above. */
+ drbd_set_my_capacity(mdev, size);
+ mdev->ldev->md.la_size_sect = size;
+ dev_info(DEV, "size = %s (%llu KB)\n", ppsize(ppb, size>>1),
+ (unsigned long long)size>>1);
+ }
+ if (rv == dev_size_error)
+ goto out;
+
+ la_size_changed = (la_size != mdev->ldev->md.la_size_sect);
+
+ md_moved = prev_first_sect != drbd_md_first_sector(mdev->ldev)
+ || prev_size != mdev->ldev->md.md_size_sect;
+
+ if (la_size_changed || md_moved) {
+ drbd_al_shrink(mdev); /* All extents inactive. */
+ dev_info(DEV, "Writing the whole bitmap, %s\n",
+ la_size_changed && md_moved ? "size changed and md moved" :
+ la_size_changed ? "size changed" : "md moved");
+ rv = drbd_bitmap_io(mdev, &drbd_bm_write, "size changed"); /* does drbd_resume_io() ! */
+ drbd_md_mark_dirty(mdev);
+ }
+
+ if (size > la_size)
+ rv = grew;
+ if (size < la_size)
+ rv = shrunk;
+out:
+ lc_unlock(mdev->act_log);
+ wake_up(&mdev->al_wait);
+ drbd_resume_io(mdev);
+
+ return rv;
+}
+
+sector_t
+drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
+{
+ sector_t p_size = mdev->p_size; /* partner's disk size. */
+ sector_t la_size = bdev->md.la_size_sect; /* last agreed size. */
+ sector_t m_size; /* my size */
+ sector_t u_size = bdev->dc.disk_size; /* size requested by user. */
+ sector_t size = 0;
+
+ m_size = drbd_get_max_capacity(bdev);
+
+ if (p_size && m_size) {
+ size = min_t(sector_t, p_size, m_size);
+ } else {
+ if (la_size) {
+ size = la_size;
+ if (m_size && m_size < size)
+ size = m_size;
+ if (p_size && p_size < size)
+ size = p_size;
+ } else {
+ if (m_size)
+ size = m_size;
+ if (p_size)
+ size = p_size;
+ }
+ }
+
+ if (size == 0)
+ dev_err(DEV, "Both nodes diskless!\n");
+
+ if (u_size) {
+ if (u_size > size)
+ dev_err(DEV, "Requested disk size is too big (%lu > %lu)\n",
+ (unsigned long)u_size>>1, (unsigned long)size>>1);
+ else
+ size = u_size;
+ }
+
+ return size;
+}
+
+/**
+ * drbd_check_al_size() - Ensures that the AL is of the right size
+ * @mdev: DRBD device.
+ *
+ * Returns -EBUSY if current al lru is still used, -ENOMEM when allocation
+ * failed, and 0 on success. You should call drbd_md_sync() after you called
+ * this function.
+ */
+static int drbd_check_al_size(struct drbd_conf *mdev)
+{
+ struct lru_cache *n, *t;
+ struct lc_element *e;
+ unsigned int in_use;
+ int i;
+
+ ERR_IF(mdev->sync_conf.al_extents < 7)
+ mdev->sync_conf.al_extents = 127;
+
+ if (mdev->act_log &&
+ mdev->act_log->nr_elements == mdev->sync_conf.al_extents)
+ return 0;
+
+ in_use = 0;
+ t = mdev->act_log;
+ n = lc_create("act_log", drbd_al_ext_cache,
+ mdev->sync_conf.al_extents, sizeof(struct lc_element), 0);
+
+ if (n == NULL) {
+ dev_err(DEV, "Cannot allocate act_log lru!\n");
+ return -ENOMEM;
+ }
+ spin_lock_irq(&mdev->al_lock);
+ if (t) {
+ for (i = 0; i < t->nr_elements; i++) {
+ e = lc_element_by_index(t, i);
+ if (e->refcnt)
+ dev_err(DEV, "refcnt(%d)==%d\n",
+ e->lc_number, e->refcnt);
+ in_use += e->refcnt;
+ }
+ }
+ if (!in_use)
+ mdev->act_log = n;
+ spin_unlock_irq(&mdev->al_lock);
+ if (in_use) {
+ dev_err(DEV, "Activity log still in use!\n");
+ lc_destroy(n);
+ return -EBUSY;
+ } else {
+ if (t)
+ lc_destroy(t);
+ }
+ drbd_md_mark_dirty(mdev); /* we changed mdev->act_log->nr_elemens */
+ return 0;
+}
+
+void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_seg_s) __must_hold(local)
+{
+ struct request_queue * const q = mdev->rq_queue;
+ struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue;
+ int max_segments = mdev->ldev->dc.max_bio_bvecs;
+
+ if (b->merge_bvec_fn && !mdev->ldev->dc.use_bmbv)
+ max_seg_s = PAGE_SIZE;
+
+ max_seg_s = min(queue_max_sectors(b) * queue_logical_block_size(b), max_seg_s);
+
+ blk_queue_max_sectors(q, max_seg_s >> 9);
+ blk_queue_max_phys_segments(q, max_segments ? max_segments : MAX_PHYS_SEGMENTS);
+ blk_queue_max_hw_segments(q, max_segments ? max_segments : MAX_HW_SEGMENTS);
+ blk_queue_max_segment_size(q, max_seg_s);
+ blk_queue_logical_block_size(q, 512);
+ blk_queue_segment_boundary(q, PAGE_SIZE-1);
+ blk_queue_stack_limits(q, b);
+
+ if (b->merge_bvec_fn)
+ dev_warn(DEV, "Backing device's merge_bvec_fn() = %p\n",
+ b->merge_bvec_fn);
+ dev_info(DEV, "max_segment_size ( = BIO size ) = %u\n", queue_max_segment_size(q));
+
+ if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
+ dev_info(DEV, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
+ q->backing_dev_info.ra_pages,
+ b->backing_dev_info.ra_pages);
+ q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
+ }
+}
+
+/* serialize deconfig (worker exiting, doing cleanup)
+ * and reconfig (drbdsetup disk, drbdsetup net)
+ *
+ * wait for a potentially exiting worker, then restart it,
+ * or start a new one.
+ */
+static void drbd_reconfig_start(struct drbd_conf *mdev)
+{
+ wait_event(mdev->state_wait, test_and_set_bit(CONFIG_PENDING, &mdev->flags));
+ wait_event(mdev->state_wait, !test_bit(DEVICE_DYING, &mdev->flags));
+ drbd_thread_start(&mdev->worker);
+}
+
+/* if still unconfigured, stops worker again.
+ * if configured now, clears CONFIG_PENDING.
+ * wakes potential waiters */
+static void drbd_reconfig_done(struct drbd_conf *mdev)
+{
+ spin_lock_irq(&mdev->req_lock);
+ if (mdev->state.disk == D_DISKLESS &&
+ mdev->state.conn == C_STANDALONE &&
+ mdev->state.role == R_SECONDARY) {
+ set_bit(DEVICE_DYING, &mdev->flags);
+ drbd_thread_stop_nowait(&mdev->worker);
+ } else
+ clear_bit(CONFIG_PENDING, &mdev->flags);
+ spin_unlock_irq(&mdev->req_lock);
+ wake_up(&mdev->state_wait);
+}
+
+/* does always return 0;
+ * interesting return code is in reply->ret_code */
+static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ enum drbd_ret_codes retcode;
+ enum determine_dev_size dd;
+ sector_t max_possible_sectors;
+ sector_t min_md_device_sectors;
+ struct drbd_backing_dev *nbc = NULL; /* new_backing_conf */
+ struct inode *inode, *inode2;
+ struct lru_cache *resync_lru = NULL;
+ union drbd_state ns, os;
+ int rv;
+ int cp_discovered = 0;
+ int logical_block_size;
+
+ drbd_reconfig_start(mdev);
+
+ /* if you want to reconfigure, please tear down first */
+ if (mdev->state.disk > D_DISKLESS) {
+ retcode = ERR_DISK_CONFIGURED;
+ goto fail;
+ }
+
+ /* allocation not in the IO path, cqueue thread context */
+ nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL);
+ if (!nbc) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+
+ nbc->dc.disk_size = DRBD_DISK_SIZE_SECT_DEF;
+ nbc->dc.on_io_error = DRBD_ON_IO_ERROR_DEF;
+ nbc->dc.fencing = DRBD_FENCING_DEF;
+ nbc->dc.max_bio_bvecs = DRBD_MAX_BIO_BVECS_DEF;
+
+ if (!disk_conf_from_tags(mdev, nlp->tag_list, &nbc->dc)) {
+ retcode = ERR_MANDATORY_TAG;
+ goto fail;
+ }
+
+ if (nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) {
+ retcode = ERR_MD_IDX_INVALID;
+ goto fail;
+ }
+
+ nbc->lo_file = filp_open(nbc->dc.backing_dev, O_RDWR, 0);
+ if (IS_ERR(nbc->lo_file)) {
+ dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.backing_dev,
+ PTR_ERR(nbc->lo_file));
+ nbc->lo_file = NULL;
+ retcode = ERR_OPEN_DISK;
+ goto fail;
+ }
+
+ inode = nbc->lo_file->f_dentry->d_inode;
+
+ if (!S_ISBLK(inode->i_mode)) {
+ retcode = ERR_DISK_NOT_BDEV;
+ goto fail;
+ }
+
+ nbc->md_file = filp_open(nbc->dc.meta_dev, O_RDWR, 0);
+ if (IS_ERR(nbc->md_file)) {
+ dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev,
+ PTR_ERR(nbc->md_file));
+ nbc->md_file = NULL;
+ retcode = ERR_OPEN_MD_DISK;
+ goto fail;
+ }
+
+ inode2 = nbc->md_file->f_dentry->d_inode;
+
+ if (!S_ISBLK(inode2->i_mode)) {
+ retcode = ERR_MD_NOT_BDEV;
+ goto fail;
+ }
+
+ nbc->backing_bdev = inode->i_bdev;
+ if (bd_claim(nbc->backing_bdev, mdev)) {
+ printk(KERN_ERR "drbd: bd_claim(%p,%p); failed [%p;%p;%u]\n",
+ nbc->backing_bdev, mdev,
+ nbc->backing_bdev->bd_holder,
+ nbc->backing_bdev->bd_contains->bd_holder,
+ nbc->backing_bdev->bd_holders);
+ retcode = ERR_BDCLAIM_DISK;
+ goto fail;
+ }
+
+ resync_lru = lc_create("resync", drbd_bm_ext_cache,
+ 61, sizeof(struct bm_extent),
+ offsetof(struct bm_extent, lce));
+ if (!resync_lru) {
+ retcode = ERR_NOMEM;
+ goto release_bdev_fail;
+ }
+
+ /* meta_dev_idx >= 0: external fixed size,
+ * possibly multiple drbd sharing one meta device.
+ * TODO in that case, paranoia check that [md_bdev, meta_dev_idx] is
+ * not yet used by some other drbd minor!
+ * (if you use drbd.conf + drbdadm,
+ * that should check it for you already; but if you don't, or someone
+ * fooled it, we need to double check here) */
+ nbc->md_bdev = inode2->i_bdev;
+ if (bd_claim(nbc->md_bdev, (nbc->dc.meta_dev_idx < 0) ? (void *)mdev
+ : (void *) drbd_m_holder)) {
+ retcode = ERR_BDCLAIM_MD_DISK;
+ goto release_bdev_fail;
+ }
+
+ if ((nbc->backing_bdev == nbc->md_bdev) !=
+ (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
+ nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) {
+ retcode = ERR_MD_IDX_INVALID;
+ goto release_bdev2_fail;
+ }
+
+ /* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */
+ drbd_md_set_sector_offsets(mdev, nbc);
+
+ if (drbd_get_max_capacity(nbc) < nbc->dc.disk_size) {
+ dev_err(DEV, "max capacity %llu smaller than disk size %llu\n",
+ (unsigned long long) drbd_get_max_capacity(nbc),
+ (unsigned long long) nbc->dc.disk_size);
+ retcode = ERR_DISK_TO_SMALL;
+ goto release_bdev2_fail;
+ }
+
+ if (nbc->dc.meta_dev_idx < 0) {
+ max_possible_sectors = DRBD_MAX_SECTORS_FLEX;
+ /* at least one MB, otherwise it does not make sense */
+ min_md_device_sectors = (2<<10);
+ } else {
+ max_possible_sectors = DRBD_MAX_SECTORS;
+ min_md_device_sectors = MD_RESERVED_SECT * (nbc->dc.meta_dev_idx + 1);
+ }
+
+ if (drbd_get_capacity(nbc->md_bdev) > max_possible_sectors)
+ dev_warn(DEV, "truncating very big lower level device "
+ "to currently maximum possible %llu sectors\n",
+ (unsigned long long) max_possible_sectors);
+
+ if (drbd_get_capacity(nbc->md_bdev) < min_md_device_sectors) {
+ retcode = ERR_MD_DISK_TO_SMALL;
+ dev_warn(DEV, "refusing attach: md-device too small, "
+ "at least %llu sectors needed for this meta-disk type\n",
+ (unsigned long long) min_md_device_sectors);
+ goto release_bdev2_fail;
+ }
+
+ /* Make sure the new disk is big enough
+ * (we may currently be R_PRIMARY with no local disk...) */
+ if (drbd_get_max_capacity(nbc) <
+ drbd_get_capacity(mdev->this_bdev)) {
+ retcode = ERR_DISK_TO_SMALL;
+ goto release_bdev2_fail;
+ }
+
+ nbc->known_size = drbd_get_capacity(nbc->backing_bdev);
+
+ drbd_suspend_io(mdev);
+ /* also wait for the last barrier ack. */
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt));
+
+ retcode = _drbd_request_state(mdev, NS(disk, D_ATTACHING), CS_VERBOSE);
+ drbd_resume_io(mdev);
+ if (retcode < SS_SUCCESS)
+ goto release_bdev2_fail;
+
+ if (!get_ldev_if_state(mdev, D_ATTACHING))
+ goto force_diskless;
+
+ drbd_md_set_sector_offsets(mdev, nbc);
+
+ if (!mdev->bitmap) {
+ if (drbd_bm_init(mdev)) {
+ retcode = ERR_NOMEM;
+ goto force_diskless_dec;
+ }
+ }
+
+ retcode = drbd_md_read(mdev, nbc);
+ if (retcode != NO_ERROR)
+ goto force_diskless_dec;
+
+ if (mdev->state.conn < C_CONNECTED &&
+ mdev->state.role == R_PRIMARY &&
+ (mdev->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) {
+ dev_err(DEV, "Can only attach to data with current UUID=%016llX\n",
+ (unsigned long long)mdev->ed_uuid);
+ retcode = ERR_DATA_NOT_CURRENT;
+ goto force_diskless_dec;
+ }
+
+ /* Since we are diskless, fix the activity log first... */
+ if (drbd_check_al_size(mdev)) {
+ retcode = ERR_NOMEM;
+ goto force_diskless_dec;
+ }
+
+ /* Prevent shrinking of consistent devices ! */
+ if (drbd_md_test_flag(nbc, MDF_CONSISTENT) &&
+ drbd_new_dev_size(mdev, nbc) < nbc->md.la_size_sect) {
+ dev_warn(DEV, "refusing to truncate a consistent device\n");
+ retcode = ERR_DISK_TO_SMALL;
+ goto force_diskless_dec;
+ }
+
+ if (!drbd_al_read_log(mdev, nbc)) {
+ retcode = ERR_IO_MD_DISK;
+ goto force_diskless_dec;
+ }
+
+ /* allocate a second IO page if logical_block_size != 512 */
+ logical_block_size = bdev_logical_block_size(nbc->md_bdev);
+ if (logical_block_size == 0)
+ logical_block_size = MD_SECTOR_SIZE;
+
+ if (logical_block_size != MD_SECTOR_SIZE) {
+ if (!mdev->md_io_tmpp) {
+ struct page *page = alloc_page(GFP_NOIO);
+ if (!page)
+ goto force_diskless_dec;
+
+ dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n",
+ logical_block_size, MD_SECTOR_SIZE);
+ dev_warn(DEV, "Workaround engaged (has performace impact).\n");
+
+ mdev->md_io_tmpp = page;
+ }
+ }
+
+ /* Reset the "barriers don't work" bits here, then force meta data to
+ * be written, to ensure we determine if barriers are supported. */
+ if (nbc->dc.no_md_flush)
+ set_bit(MD_NO_BARRIER, &mdev->flags);
+ else
+ clear_bit(MD_NO_BARRIER, &mdev->flags);
+
+ /* Point of no return reached.
+ * Devices and memory are no longer released by error cleanup below.
+ * now mdev takes over responsibility, and the state engine should
+ * clean it up somewhere. */
+ D_ASSERT(mdev->ldev == NULL);
+ mdev->ldev = nbc;
+ mdev->resync = resync_lru;
+ nbc = NULL;
+ resync_lru = NULL;
+
+ mdev->write_ordering = WO_bio_barrier;
+ drbd_bump_write_ordering(mdev, WO_bio_barrier);
+
+ if (drbd_md_test_flag(mdev->ldev, MDF_CRASHED_PRIMARY))
+ set_bit(CRASHED_PRIMARY, &mdev->flags);
+ else
+ clear_bit(CRASHED_PRIMARY, &mdev->flags);
+
+ if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND)) {
+ set_bit(CRASHED_PRIMARY, &mdev->flags);
+ cp_discovered = 1;
+ }
+
+ mdev->send_cnt = 0;
+ mdev->recv_cnt = 0;
+ mdev->read_cnt = 0;
+ mdev->writ_cnt = 0;
+
+ drbd_setup_queue_param(mdev, DRBD_MAX_SEGMENT_SIZE);
+
+ /* If I am currently not R_PRIMARY,
+ * but meta data primary indicator is set,
+ * I just now recover from a hard crash,
+ * and have been R_PRIMARY before that crash.
+ *
+ * Now, if I had no connection before that crash
+ * (have been degraded R_PRIMARY), chances are that
+ * I won't find my peer now either.
+ *
+ * In that case, and _only_ in that case,
+ * we use the degr-wfc-timeout instead of the default,
+ * so we can automatically recover from a crash of a
+ * degraded but active "cluster" after a certain timeout.
+ */
+ clear_bit(USE_DEGR_WFC_T, &mdev->flags);
+ if (mdev->state.role != R_PRIMARY &&
+ drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) &&
+ !drbd_md_test_flag(mdev->ldev, MDF_CONNECTED_IND))
+ set_bit(USE_DEGR_WFC_T, &mdev->flags);
+
+ dd = drbd_determin_dev_size(mdev);
+ if (dd == dev_size_error) {
+ retcode = ERR_NOMEM_BITMAP;
+ goto force_diskless_dec;
+ } else if (dd == grew)
+ set_bit(RESYNC_AFTER_NEG, &mdev->flags);
+
+ if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) {
+ dev_info(DEV, "Assuming that all blocks are out of sync "
+ "(aka FullSync)\n");
+ if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, "set_n_write from attaching")) {
+ retcode = ERR_IO_MD_DISK;
+ goto force_diskless_dec;
+ }
+ } else {
+ if (drbd_bitmap_io(mdev, &drbd_bm_read, "read from attaching") < 0) {
+ retcode = ERR_IO_MD_DISK;
+ goto force_diskless_dec;
+ }
+ }
+
+ if (cp_discovered) {
+ drbd_al_apply_to_bm(mdev);
+ drbd_al_to_on_disk_bm(mdev);
+ }
+
+ spin_lock_irq(&mdev->req_lock);
+ os = mdev->state;
+ ns.i = os.i;
+ /* If MDF_CONSISTENT is not set go into inconsistent state,
+ otherwise investige MDF_WasUpToDate...
+ If MDF_WAS_UP_TO_DATE is not set go into D_OUTDATED disk state,
+ otherwise into D_CONSISTENT state.
+ */
+ if (drbd_md_test_flag(mdev->ldev, MDF_CONSISTENT)) {
+ if (drbd_md_test_flag(mdev->ldev, MDF_WAS_UP_TO_DATE))
+ ns.disk = D_CONSISTENT;
+ else
+ ns.disk = D_OUTDATED;
+ } else {
+ ns.disk = D_INCONSISTENT;
+ }
+
+ if (drbd_md_test_flag(mdev->ldev, MDF_PEER_OUT_DATED))
+ ns.pdsk = D_OUTDATED;
+
+ if ( ns.disk == D_CONSISTENT &&
+ (ns.pdsk == D_OUTDATED || mdev->ldev->dc.fencing == FP_DONT_CARE))
+ ns.disk = D_UP_TO_DATE;
+
+ /* All tests on MDF_PRIMARY_IND, MDF_CONNECTED_IND,
+ MDF_CONSISTENT and MDF_WAS_UP_TO_DATE must happen before
+ this point, because drbd_request_state() modifies these
+ flags. */
+
+ /* In case we are C_CONNECTED postpone any desicion on the new disk
+ state after the negotiation phase. */
+ if (mdev->state.conn == C_CONNECTED) {
+ mdev->new_state_tmp.i = ns.i;
+ ns.i = os.i;
+ ns.disk = D_NEGOTIATING;
+ }
+
+ rv = _drbd_set_state(mdev, ns, CS_VERBOSE, NULL);
+ ns = mdev->state;
+ spin_unlock_irq(&mdev->req_lock);
+
+ if (rv < SS_SUCCESS)
+ goto force_diskless_dec;
+
+ if (mdev->state.role == R_PRIMARY)
+ mdev->ldev->md.uuid[UI_CURRENT] |= (u64)1;
+ else
+ mdev->ldev->md.uuid[UI_CURRENT] &= ~(u64)1;
+
+ drbd_md_mark_dirty(mdev);
+ drbd_md_sync(mdev);
+
+ kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
+ put_ldev(mdev);
+ reply->ret_code = retcode;
+ drbd_reconfig_done(mdev);
+ return 0;
+
+ force_diskless_dec:
+ put_ldev(mdev);
+ force_diskless:
+ drbd_force_state(mdev, NS(disk, D_DISKLESS));
+ drbd_md_sync(mdev);
+ release_bdev2_fail:
+ if (nbc)
+ bd_release(nbc->md_bdev);
+ release_bdev_fail:
+ if (nbc)
+ bd_release(nbc->backing_bdev);
+ fail:
+ if (nbc) {
+ if (nbc->lo_file)
+ fput(nbc->lo_file);
+ if (nbc->md_file)
+ fput(nbc->md_file);
+ kfree(nbc);
+ }
+ lc_destroy(resync_lru);
+
+ reply->ret_code = retcode;
+ drbd_reconfig_done(mdev);
+ return 0;
+}
+
+static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS));
+ return 0;
+}
+
+static int drbd_nl_net_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int i, ns;
+ enum drbd_ret_codes retcode;
+ struct net_conf *new_conf = NULL;
+ struct crypto_hash *tfm = NULL;
+ struct crypto_hash *integrity_w_tfm = NULL;
+ struct crypto_hash *integrity_r_tfm = NULL;
+ struct hlist_head *new_tl_hash = NULL;
+ struct hlist_head *new_ee_hash = NULL;
+ struct drbd_conf *odev;
+ char hmac_name[CRYPTO_MAX_ALG_NAME];
+ void *int_dig_out = NULL;
+ void *int_dig_in = NULL;
+ void *int_dig_vv = NULL;
+ struct sockaddr *new_my_addr, *new_peer_addr, *taken_addr;
+
+ drbd_reconfig_start(mdev);
+
+ if (mdev->state.conn > C_STANDALONE) {
+ retcode = ERR_NET_CONFIGURED;
+ goto fail;
+ }
+
+ /* allocation not in the IO path, cqueue thread context */
+ new_conf = kmalloc(sizeof(struct net_conf), GFP_KERNEL);
+ if (!new_conf) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+
+ memset(new_conf, 0, sizeof(struct net_conf));
+ new_conf->timeout = DRBD_TIMEOUT_DEF;
+ new_conf->try_connect_int = DRBD_CONNECT_INT_DEF;
+ new_conf->ping_int = DRBD_PING_INT_DEF;
+ new_conf->max_epoch_size = DRBD_MAX_EPOCH_SIZE_DEF;
+ new_conf->max_buffers = DRBD_MAX_BUFFERS_DEF;
+ new_conf->unplug_watermark = DRBD_UNPLUG_WATERMARK_DEF;
+ new_conf->sndbuf_size = DRBD_SNDBUF_SIZE_DEF;
+ new_conf->rcvbuf_size = DRBD_RCVBUF_SIZE_DEF;
+ new_conf->ko_count = DRBD_KO_COUNT_DEF;
+ new_conf->after_sb_0p = DRBD_AFTER_SB_0P_DEF;
+ new_conf->after_sb_1p = DRBD_AFTER_SB_1P_DEF;
+ new_conf->after_sb_2p = DRBD_AFTER_SB_2P_DEF;
+ new_conf->want_lose = 0;
+ new_conf->two_primaries = 0;
+ new_conf->wire_protocol = DRBD_PROT_C;
+ new_conf->ping_timeo = DRBD_PING_TIMEO_DEF;
+ new_conf->rr_conflict = DRBD_RR_CONFLICT_DEF;
+
+ if (!net_conf_from_tags(mdev, nlp->tag_list, new_conf)) {
+ retcode = ERR_MANDATORY_TAG;
+ goto fail;
+ }
+
+ if (new_conf->two_primaries
+ && (new_conf->wire_protocol != DRBD_PROT_C)) {
+ retcode = ERR_NOT_PROTO_C;
+ goto fail;
+ };
+
+ if (mdev->state.role == R_PRIMARY && new_conf->want_lose) {
+ retcode = ERR_DISCARD;
+ goto fail;
+ }
+
+ retcode = NO_ERROR;
+
+ new_my_addr = (struct sockaddr *)&new_conf->my_addr;
+ new_peer_addr = (struct sockaddr *)&new_conf->peer_addr;
+ for (i = 0; i < minor_count; i++) {
+ odev = minor_to_mdev(i);
+ if (!odev || odev == mdev)
+ continue;
+ if (get_net_conf(odev)) {
+ taken_addr = (struct sockaddr *)&odev->net_conf->my_addr;
+ if (new_conf->my_addr_len == odev->net_conf->my_addr_len &&
+ !memcmp(new_my_addr, taken_addr, new_conf->my_addr_len))
+ retcode = ERR_LOCAL_ADDR;
+
+ taken_addr = (struct sockaddr *)&odev->net_conf->peer_addr;
+ if (new_conf->peer_addr_len == odev->net_conf->peer_addr_len &&
+ !memcmp(new_peer_addr, taken_addr, new_conf->peer_addr_len))
+ retcode = ERR_PEER_ADDR;
+
+ put_net_conf(odev);
+ if (retcode != NO_ERROR)
+ goto fail;
+ }
+ }
+
+ if (new_conf->cram_hmac_alg[0] != 0) {
+ snprintf(hmac_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)",
+ new_conf->cram_hmac_alg);
+ tfm = crypto_alloc_hash(hmac_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm)) {
+ tfm = NULL;
+ retcode = ERR_AUTH_ALG;
+ goto fail;
+ }
+
+ if (crypto_tfm_alg_type(crypto_hash_tfm(tfm))
+ != CRYPTO_ALG_TYPE_HASH) {
+ retcode = ERR_AUTH_ALG_ND;
+ goto fail;
+ }
+ }
+
+ if (new_conf->integrity_alg[0]) {
+ integrity_w_tfm = crypto_alloc_hash(new_conf->integrity_alg, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(integrity_w_tfm)) {
+ integrity_w_tfm = NULL;
+ retcode=ERR_INTEGRITY_ALG;
+ goto fail;
+ }
+
+ if (!drbd_crypto_is_hash(crypto_hash_tfm(integrity_w_tfm))) {
+ retcode=ERR_INTEGRITY_ALG_ND;
+ goto fail;
+ }
+
+ integrity_r_tfm = crypto_alloc_hash(new_conf->integrity_alg, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(integrity_r_tfm)) {
+ integrity_r_tfm = NULL;
+ retcode=ERR_INTEGRITY_ALG;
+ goto fail;
+ }
+ }
+
+ ns = new_conf->max_epoch_size/8;
+ if (mdev->tl_hash_s != ns) {
+ new_tl_hash = kzalloc(ns*sizeof(void *), GFP_KERNEL);
+ if (!new_tl_hash) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ }
+
+ ns = new_conf->max_buffers/8;
+ if (new_conf->two_primaries && (mdev->ee_hash_s != ns)) {
+ new_ee_hash = kzalloc(ns*sizeof(void *), GFP_KERNEL);
+ if (!new_ee_hash) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ }
+
+ ((char *)new_conf->shared_secret)[SHARED_SECRET_MAX-1] = 0;
+
+ if (integrity_w_tfm) {
+ i = crypto_hash_digestsize(integrity_w_tfm);
+ int_dig_out = kmalloc(i, GFP_KERNEL);
+ if (!int_dig_out) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ int_dig_in = kmalloc(i, GFP_KERNEL);
+ if (!int_dig_in) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ int_dig_vv = kmalloc(i, GFP_KERNEL);
+ if (!int_dig_vv) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ }
+
+ if (!mdev->bitmap) {
+ if(drbd_bm_init(mdev)) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ }
+
+ spin_lock_irq(&mdev->req_lock);
+ if (mdev->net_conf != NULL) {
+ retcode = ERR_NET_CONFIGURED;
+ spin_unlock_irq(&mdev->req_lock);
+ goto fail;
+ }
+ mdev->net_conf = new_conf;
+
+ mdev->send_cnt = 0;
+ mdev->recv_cnt = 0;
+
+ if (new_tl_hash) {
+ kfree(mdev->tl_hash);
+ mdev->tl_hash_s = mdev->net_conf->max_epoch_size/8;
+ mdev->tl_hash = new_tl_hash;
+ }
+
+ if (new_ee_hash) {
+ kfree(mdev->ee_hash);
+ mdev->ee_hash_s = mdev->net_conf->max_buffers/8;
+ mdev->ee_hash = new_ee_hash;
+ }
+
+ crypto_free_hash(mdev->cram_hmac_tfm);
+ mdev->cram_hmac_tfm = tfm;
+
+ crypto_free_hash(mdev->integrity_w_tfm);
+ mdev->integrity_w_tfm = integrity_w_tfm;
+
+ crypto_free_hash(mdev->integrity_r_tfm);
+ mdev->integrity_r_tfm = integrity_r_tfm;
+
+ kfree(mdev->int_dig_out);
+ kfree(mdev->int_dig_in);
+ kfree(mdev->int_dig_vv);
+ mdev->int_dig_out=int_dig_out;
+ mdev->int_dig_in=int_dig_in;
+ mdev->int_dig_vv=int_dig_vv;
+ spin_unlock_irq(&mdev->req_lock);
+
+ retcode = _drbd_request_state(mdev, NS(conn, C_UNCONNECTED), CS_VERBOSE);
+
+ kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
+ reply->ret_code = retcode;
+ drbd_reconfig_done(mdev);
+ return 0;
+
+fail:
+ kfree(int_dig_out);
+ kfree(int_dig_in);
+ kfree(int_dig_vv);
+ crypto_free_hash(tfm);
+ crypto_free_hash(integrity_w_tfm);
+ crypto_free_hash(integrity_r_tfm);
+ kfree(new_tl_hash);
+ kfree(new_ee_hash);
+ kfree(new_conf);
+
+ reply->ret_code = retcode;
+ drbd_reconfig_done(mdev);
+ return 0;
+}
+
+static int drbd_nl_disconnect(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int retcode;
+
+ retcode = _drbd_request_state(mdev, NS(conn, C_DISCONNECTING), CS_ORDERED);
+
+ if (retcode == SS_NOTHING_TO_DO)
+ goto done;
+ else if (retcode == SS_ALREADY_STANDALONE)
+ goto done;
+ else if (retcode == SS_PRIMARY_NOP) {
+ /* Our statche checking code wants to see the peer outdated. */
+ retcode = drbd_request_state(mdev, NS2(conn, C_DISCONNECTING,
+ pdsk, D_OUTDATED));
+ } else if (retcode == SS_CW_FAILED_BY_PEER) {
+ /* The peer probabely wants to see us outdated. */
+ retcode = _drbd_request_state(mdev, NS2(conn, C_DISCONNECTING,
+ disk, D_OUTDATED),
+ CS_ORDERED);
+ if (retcode == SS_IS_DISKLESS || retcode == SS_LOWER_THAN_OUTDATED) {
+ drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
+ retcode = SS_SUCCESS;
+ }
+ }
+
+ if (retcode < SS_SUCCESS)
+ goto fail;
+
+ if (wait_event_interruptible(mdev->state_wait,
+ mdev->state.conn != C_DISCONNECTING)) {
+ /* Do not test for mdev->state.conn == C_STANDALONE, since
+ someone else might connect us in the mean time! */
+ retcode = ERR_INTR;
+ goto fail;
+ }
+
+ done:
+ retcode = NO_ERROR;
+ fail:
+ drbd_md_sync(mdev);
+ reply->ret_code = retcode;
+ return 0;
+}
+
+void resync_after_online_grow(struct drbd_conf *mdev)
+{
+ int iass; /* I am sync source */
+
+ dev_info(DEV, "Resync of new storage after online grow\n");
+ if (mdev->state.role != mdev->state.peer)
+ iass = (mdev->state.role == R_PRIMARY);
+ else
+ iass = test_bit(DISCARD_CONCURRENT, &mdev->flags);
+
+ if (iass)
+ drbd_start_resync(mdev, C_SYNC_SOURCE);
+ else
+ _drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE + CS_SERIALIZE);
+}
+
+static int drbd_nl_resize(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ struct resize rs;
+ int retcode = NO_ERROR;
+ int ldsc = 0; /* local disk size changed */
+ enum determine_dev_size dd;
+
+ memset(&rs, 0, sizeof(struct resize));
+ if (!resize_from_tags(mdev, nlp->tag_list, &rs)) {
+ retcode = ERR_MANDATORY_TAG;
+ goto fail;
+ }
+
+ if (mdev->state.conn > C_CONNECTED) {
+ retcode = ERR_RESIZE_RESYNC;
+ goto fail;
+ }
+
+ if (mdev->state.role == R_SECONDARY &&
+ mdev->state.peer == R_SECONDARY) {
+ retcode = ERR_NO_PRIMARY;
+ goto fail;
+ }
+
+ if (!get_ldev(mdev)) {
+ retcode = ERR_NO_DISK;
+ goto fail;
+ }
+
+ if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev)) {
+ mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev);
+ ldsc = 1;
+ }
+
+ mdev->ldev->dc.disk_size = (sector_t)rs.resize_size;
+ dd = drbd_determin_dev_size(mdev);
+ drbd_md_sync(mdev);
+ put_ldev(mdev);
+ if (dd == dev_size_error) {
+ retcode = ERR_NOMEM_BITMAP;
+ goto fail;
+ }
+
+ if (mdev->state.conn == C_CONNECTED && (dd != unchanged || ldsc)) {
+ if (dd == grew)
+ set_bit(RESIZE_PENDING, &mdev->flags);
+
+ drbd_send_uuids(mdev);
+ drbd_send_sizes(mdev, 1);
+ }
+
+ fail:
+ reply->ret_code = retcode;
+ return 0;
+}
+
+static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int retcode = NO_ERROR;
+ int err;
+ int ovr; /* online verify running */
+ int rsr; /* re-sync running */
+ struct crypto_hash *verify_tfm = NULL;
+ struct crypto_hash *csums_tfm = NULL;
+ struct syncer_conf sc;
+ cpumask_t n_cpu_mask = CPU_MASK_NONE;
+
+ memcpy(&sc, &mdev->sync_conf, sizeof(struct syncer_conf));
+
+ if (nlp->flags & DRBD_NL_SET_DEFAULTS) {
+ memset(&sc, 0, sizeof(struct syncer_conf));
+ sc.rate = DRBD_RATE_DEF;
+ sc.after = DRBD_AFTER_DEF;
+ sc.al_extents = DRBD_AL_EXTENTS_DEF;
+ }
+
+ if (!syncer_conf_from_tags(mdev, nlp->tag_list, &sc)) {
+ retcode = ERR_MANDATORY_TAG;
+ goto fail;
+ }
+
+ /* re-sync running */
+ rsr = ( mdev->state.conn == C_SYNC_SOURCE ||
+ mdev->state.conn == C_SYNC_TARGET ||
+ mdev->state.conn == C_PAUSED_SYNC_S ||
+ mdev->state.conn == C_PAUSED_SYNC_T );
+
+ if (rsr && strcmp(sc.csums_alg, mdev->sync_conf.csums_alg)) {
+ retcode = ERR_CSUMS_RESYNC_RUNNING;
+ goto fail;
+ }
+
+ if (!rsr && sc.csums_alg[0]) {
+ csums_tfm = crypto_alloc_hash(sc.csums_alg, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(csums_tfm)) {
+ csums_tfm = NULL;
+ retcode = ERR_CSUMS_ALG;
+ goto fail;
+ }
+
+ if (!drbd_crypto_is_hash(crypto_hash_tfm(csums_tfm))) {
+ retcode = ERR_CSUMS_ALG_ND;
+ goto fail;
+ }
+ }
+
+ /* online verify running */
+ ovr = (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T);
+
+ if (ovr) {
+ if (strcmp(sc.verify_alg, mdev->sync_conf.verify_alg)) {
+ retcode = ERR_VERIFY_RUNNING;
+ goto fail;
+ }
+ }
+
+ if (!ovr && sc.verify_alg[0]) {
+ verify_tfm = crypto_alloc_hash(sc.verify_alg, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(verify_tfm)) {
+ verify_tfm = NULL;
+ retcode = ERR_VERIFY_ALG;
+ goto fail;
+ }
+
+ if (!drbd_crypto_is_hash(crypto_hash_tfm(verify_tfm))) {
+ retcode = ERR_VERIFY_ALG_ND;
+ goto fail;
+ }
+ }
+
+ /* silently ignore cpu mask on UP kernel */
+ if (NR_CPUS > 1 && sc.cpu_mask[0] != 0) {
+ err = __bitmap_parse(sc.cpu_mask, 32, 0, (unsigned long *)&n_cpu_mask, NR_CPUS);
+ if (err) {
+ dev_warn(DEV, "__bitmap_parse() failed with %d\n", err);
+ retcode = ERR_CPU_MASK_PARSE;
+ goto fail;
+ }
+ }
+
+ ERR_IF (sc.rate < 1) sc.rate = 1;
+ ERR_IF (sc.al_extents < 7) sc.al_extents = 127; /* arbitrary minimum */
+#define AL_MAX ((MD_AL_MAX_SIZE-1) * AL_EXTENTS_PT)
+ if (sc.al_extents > AL_MAX) {
+ dev_err(DEV, "sc.al_extents > %d\n", AL_MAX);
+ sc.al_extents = AL_MAX;
+ }
+#undef AL_MAX
+
+ /* most sanity checks done, try to assign the new sync-after
+ * dependency. need to hold the global lock in there,
+ * to avoid a race in the dependency loop check. */
+ retcode = drbd_alter_sa(mdev, sc.after);
+ if (retcode != NO_ERROR)
+ goto fail;
+
+ /* ok, assign the rest of it as well.
+ * lock against receive_SyncParam() */
+ spin_lock(&mdev->peer_seq_lock);
+ mdev->sync_conf = sc;
+
+ if (!rsr) {
+ crypto_free_hash(mdev->csums_tfm);
+ mdev->csums_tfm = csums_tfm;
+ csums_tfm = NULL;
+ }
+
+ if (!ovr) {
+ crypto_free_hash(mdev->verify_tfm);
+ mdev->verify_tfm = verify_tfm;
+ verify_tfm = NULL;
+ }
+ spin_unlock(&mdev->peer_seq_lock);
+
+ if (get_ldev(mdev)) {
+ wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
+ drbd_al_shrink(mdev);
+ err = drbd_check_al_size(mdev);
+ lc_unlock(mdev->act_log);
+ wake_up(&mdev->al_wait);
+
+ put_ldev(mdev);
+ drbd_md_sync(mdev);
+
+ if (err) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ }
+
+ if (mdev->state.conn >= C_CONNECTED)
+ drbd_send_sync_param(mdev, &sc);
+
+ if (!cpus_equal(mdev->cpu_mask, n_cpu_mask)) {
+ mdev->cpu_mask = n_cpu_mask;
+ mdev->cpu_mask = drbd_calc_cpu_mask(mdev);
+ mdev->receiver.reset_cpu_mask = 1;
+ mdev->asender.reset_cpu_mask = 1;
+ mdev->worker.reset_cpu_mask = 1;
+ }
+
+ kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
+fail:
+ crypto_free_hash(csums_tfm);
+ crypto_free_hash(verify_tfm);
+ reply->ret_code = retcode;
+ return 0;
+}
+
+static int drbd_nl_invalidate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int retcode;
+
+ retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED);
+
+ if (retcode < SS_SUCCESS && retcode != SS_NEED_CONNECTION)
+ retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
+
+ while (retcode == SS_NEED_CONNECTION) {
+ spin_lock_irq(&mdev->req_lock);
+ if (mdev->state.conn < C_CONNECTED)
+ retcode = _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_VERBOSE, NULL);
+ spin_unlock_irq(&mdev->req_lock);
+
+ if (retcode != SS_NEED_CONNECTION)
+ break;
+
+ retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
+ }
+
+ reply->ret_code = retcode;
+ return 0;
+}
+
+static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+
+ reply->ret_code = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
+
+ return 0;
+}
+
+static int drbd_nl_pause_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int retcode = NO_ERROR;
+
+ if (drbd_request_state(mdev, NS(user_isp, 1)) == SS_NOTHING_TO_DO)
+ retcode = ERR_PAUSE_IS_SET;
+
+ reply->ret_code = retcode;
+ return 0;
+}
+
+static int drbd_nl_resume_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int retcode = NO_ERROR;
+
+ if (drbd_request_state(mdev, NS(user_isp, 0)) == SS_NOTHING_TO_DO)
+ retcode = ERR_PAUSE_IS_CLEAR;
+
+ reply->ret_code = retcode;
+ return 0;
+}
+
+static int drbd_nl_suspend_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ reply->ret_code = drbd_request_state(mdev, NS(susp, 1));
+
+ return 0;
+}
+
+static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ reply->ret_code = drbd_request_state(mdev, NS(susp, 0));
+ return 0;
+}
+
+static int drbd_nl_outdate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ reply->ret_code = drbd_request_state(mdev, NS(disk, D_OUTDATED));
+ return 0;
+}
+
+static int drbd_nl_get_config(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ unsigned short *tl;
+
+ tl = reply->tag_list;
+
+ if (get_ldev(mdev)) {
+ tl = disk_conf_to_tags(mdev, &mdev->ldev->dc, tl);
+ put_ldev(mdev);
+ }
+
+ if (get_net_conf(mdev)) {
+ tl = net_conf_to_tags(mdev, mdev->net_conf, tl);
+ put_net_conf(mdev);
+ }
+ tl = syncer_conf_to_tags(mdev, &mdev->sync_conf, tl);
+
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ return (int)((char *)tl - (char *)reply->tag_list);
+}
+
+static int drbd_nl_get_state(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ unsigned short *tl = reply->tag_list;
+ union drbd_state s = mdev->state;
+ unsigned long rs_left;
+ unsigned int res;
+
+ tl = get_state_to_tags(mdev, (struct get_state *)&s, tl);
+
+ /* no local ref, no bitmap, no syncer progress. */
+ if (s.conn >= C_SYNC_SOURCE && s.conn <= C_PAUSED_SYNC_T) {
+ if (get_ldev(mdev)) {
+ drbd_get_syncer_progress(mdev, &rs_left, &res);
+ tl = tl_add_int(tl, T_sync_progress, &res);
+ put_ldev(mdev);
+ }
+ }
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ return (int)((char *)tl - (char *)reply->tag_list);
+}
+
+static int drbd_nl_get_uuids(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ unsigned short *tl;
+
+ tl = reply->tag_list;
+
+ if (get_ldev(mdev)) {
+ tl = tl_add_blob(tl, T_uuids, mdev->ldev->md.uuid, UI_SIZE*sizeof(u64));
+ tl = tl_add_int(tl, T_uuids_flags, &mdev->ldev->md.flags);
+ put_ldev(mdev);
+ }
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ return (int)((char *)tl - (char *)reply->tag_list);
+}
+
+/**
+ * drbd_nl_get_timeout_flag() - Used by drbdsetup to find out which timeout value to use
+ * @mdev: DRBD device.
+ * @nlp: Netlink/connector packet from drbdsetup
+ * @reply: Reply packet for drbdsetup
+ */
+static int drbd_nl_get_timeout_flag(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ unsigned short *tl;
+ char rv;
+
+ tl = reply->tag_list;
+
+ rv = mdev->state.pdsk == D_OUTDATED ? UT_PEER_OUTDATED :
+ test_bit(USE_DEGR_WFC_T, &mdev->flags) ? UT_DEGRADED : UT_DEFAULT;
+
+ tl = tl_add_blob(tl, T_use_degraded, &rv, sizeof(rv));
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ return (int)((char *)tl - (char *)reply->tag_list);
+}
+
+static int drbd_nl_start_ov(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ /* default to resume from last known position, if possible */
+ struct start_ov args =
+ { .start_sector = mdev->ov_start_sector };
+
+ if (!start_ov_from_tags(mdev, nlp->tag_list, &args)) {
+ reply->ret_code = ERR_MANDATORY_TAG;
+ return 0;
+ }
+ /* w_make_ov_request expects position to be aligned */
+ mdev->ov_start_sector = args.start_sector & ~BM_SECT_PER_BIT;
+ reply->ret_code = drbd_request_state(mdev,NS(conn,C_VERIFY_S));
+ return 0;
+}
+
+
+static int drbd_nl_new_c_uuid(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+ struct drbd_nl_cfg_reply *reply)
+{
+ int retcode = NO_ERROR;
+ int skip_initial_sync = 0;
+ int err;
+
+ struct new_c_uuid args;
+
+ memset(&args, 0, sizeof(struct new_c_uuid));
+ if (!new_c_uuid_from_tags(mdev, nlp->tag_list, &args)) {
+ reply->ret_code = ERR_MANDATORY_TAG;
+ return 0;
+ }
+
+ mutex_lock(&mdev->state_mutex); /* Protects us against serialized state changes. */
+
+ if (!get_ldev(mdev)) {
+ retcode = ERR_NO_DISK;
+ goto out;
+ }
+
+ /* this is "skip initial sync", assume to be clean */
+ if (mdev->state.conn == C_CONNECTED && mdev->agreed_pro_version >= 90 &&
+ mdev->ldev->md.uuid[UI_CURRENT] == UUID_JUST_CREATED && args.clear_bm) {
+ dev_info(DEV, "Preparing to skip initial sync\n");
+ skip_initial_sync = 1;
+ } else if (mdev->state.conn != C_STANDALONE) {
+ retcode = ERR_CONNECTED;
+ goto out_dec;
+ }
+
+ drbd_uuid_set(mdev, UI_BITMAP, 0); /* Rotate UI_BITMAP to History 1, etc... */
+ drbd_uuid_new_current(mdev); /* New current, previous to UI_BITMAP */
+
+ if (args.clear_bm) {
+ err = drbd_bitmap_io(mdev, &drbd_bmio_clear_n_write, "clear_n_write from new_c_uuid");
+ if (err) {
+ dev_err(DEV, "Writing bitmap failed with %d\n",err);
+ retcode = ERR_IO_MD_DISK;
+ }
+ if (skip_initial_sync) {
+ drbd_send_uuids_skip_initial_sync(mdev);
+ _drbd_uuid_set(mdev, UI_BITMAP, 0);
+ spin_lock_irq(&mdev->req_lock);
+ _drbd_set_state(_NS2(mdev, disk, D_UP_TO_DATE, pdsk, D_UP_TO_DATE),
+ CS_VERBOSE, NULL);
+ spin_unlock_irq(&mdev->req_lock);
+ }
+ }
+
+ drbd_md_sync(mdev);
+out_dec:
+ put_ldev(mdev);
+out:
+ mutex_unlock(&mdev->state_mutex);
+
+ reply->ret_code = retcode;
+ return 0;
+}
+
+static struct drbd_conf *ensure_mdev(struct drbd_nl_cfg_req *nlp)
+{
+ struct drbd_conf *mdev;
+
+ if (nlp->drbd_minor >= minor_count)
+ return NULL;
+
+ mdev = minor_to_mdev(nlp->drbd_minor);
+
+ if (!mdev && (nlp->flags & DRBD_NL_CREATE_DEVICE)) {
+ struct gendisk *disk = NULL;
+ mdev = drbd_new_device(nlp->drbd_minor);
+
+ spin_lock_irq(&drbd_pp_lock);
+ if (minor_table[nlp->drbd_minor] == NULL) {
+ minor_table[nlp->drbd_minor] = mdev;
+ disk = mdev->vdisk;
+ mdev = NULL;
+ } /* else: we lost the race */
+ spin_unlock_irq(&drbd_pp_lock);
+
+ if (disk) /* we won the race above */
+ /* in case we ever add a drbd_delete_device(),
+ * don't forget the del_gendisk! */
+ add_disk(disk);
+ else /* we lost the race above */
+ drbd_free_mdev(mdev);
+
+ mdev = minor_to_mdev(nlp->drbd_minor);
+ }
+
+ return mdev;
+}
+
+struct cn_handler_struct {
+ int (*function)(struct drbd_conf *,
+ struct drbd_nl_cfg_req *,
+ struct drbd_nl_cfg_reply *);
+ int reply_body_size;
+};
+
+static struct cn_handler_struct cnd_table[] = {
+ [ P_primary ] = { &drbd_nl_primary, 0 },
+ [ P_secondary ] = { &drbd_nl_secondary, 0 },
+ [ P_disk_conf ] = { &drbd_nl_disk_conf, 0 },
+ [ P_detach ] = { &drbd_nl_detach, 0 },
+ [ P_net_conf ] = { &drbd_nl_net_conf, 0 },
+ [ P_disconnect ] = { &drbd_nl_disconnect, 0 },
+ [ P_resize ] = { &drbd_nl_resize, 0 },
+ [ P_syncer_conf ] = { &drbd_nl_syncer_conf, 0 },
+ [ P_invalidate ] = { &drbd_nl_invalidate, 0 },
+ [ P_invalidate_peer ] = { &drbd_nl_invalidate_peer, 0 },
+ [ P_pause_sync ] = { &drbd_nl_pause_sync, 0 },
+ [ P_resume_sync ] = { &drbd_nl_resume_sync, 0 },
+ [ P_suspend_io ] = { &drbd_nl_suspend_io, 0 },
+ [ P_resume_io ] = { &drbd_nl_resume_io, 0 },
+ [ P_outdate ] = { &drbd_nl_outdate, 0 },
+ [ P_get_config ] = { &drbd_nl_get_config,
+ sizeof(struct syncer_conf_tag_len_struct) +
+ sizeof(struct disk_conf_tag_len_struct) +
+ sizeof(struct net_conf_tag_len_struct) },
+ [ P_get_state ] = { &drbd_nl_get_state,
+ sizeof(struct get_state_tag_len_struct) +
+ sizeof(struct sync_progress_tag_len_struct) },
+ [ P_get_uuids ] = { &drbd_nl_get_uuids,
+ sizeof(struct get_uuids_tag_len_struct) },
+ [ P_get_timeout_flag ] = { &drbd_nl_get_timeout_flag,
+ sizeof(struct get_timeout_flag_tag_len_struct)},
+ [ P_start_ov ] = { &drbd_nl_start_ov, 0 },
+ [ P_new_c_uuid ] = { &drbd_nl_new_c_uuid, 0 },
+};
+
+static void drbd_connector_callback(void *data)
+{
+ struct cn_msg *req = data;
+ struct drbd_nl_cfg_req *nlp = (struct drbd_nl_cfg_req *)req->data;
+ struct cn_handler_struct *cm;
+ struct cn_msg *cn_reply;
+ struct drbd_nl_cfg_reply *reply;
+ struct drbd_conf *mdev;
+ int retcode, rr;
+ int reply_size = sizeof(struct cn_msg)
+ + sizeof(struct drbd_nl_cfg_reply)
+ + sizeof(short int);
+
+ if (!try_module_get(THIS_MODULE)) {
+ printk(KERN_ERR "drbd: try_module_get() failed!\n");
+ return;
+ }
+
+ mdev = ensure_mdev(nlp);
+ if (!mdev) {
+ retcode = ERR_MINOR_INVALID;
+ goto fail;
+ }
+
+ trace_drbd_netlink(data, 1);
+
+ if (nlp->packet_type >= P_nl_after_last_packet) {
+ retcode = ERR_PACKET_NR;
+ goto fail;
+ }
+
+ cm = cnd_table + nlp->packet_type;
+
+ /* This may happen if packet number is 0: */
+ if (cm->function == NULL) {
+ retcode = ERR_PACKET_NR;
+ goto fail;
+ }
+
+ reply_size += cm->reply_body_size;
+
+ /* allocation not in the IO path, cqueue thread context */
+ cn_reply = kmalloc(reply_size, GFP_KERNEL);
+ if (!cn_reply) {
+ retcode = ERR_NOMEM;
+ goto fail;
+ }
+ reply = (struct drbd_nl_cfg_reply *) cn_reply->data;
+
+ reply->packet_type =
+ cm->reply_body_size ? nlp->packet_type : P_nl_after_last_packet;
+ reply->minor = nlp->drbd_minor;
+ reply->ret_code = NO_ERROR; /* Might by modified by cm->function. */
+ /* reply->tag_list; might be modified by cm->fucntion. */
+
+ rr = cm->function(mdev, nlp, reply);
+
+ cn_reply->id = req->id;
+ cn_reply->seq = req->seq;
+ cn_reply->ack = req->ack + 1;
+ cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + rr;
+ cn_reply->flags = 0;
+
+ trace_drbd_netlink(cn_reply, 0);
+ rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
+ if (rr && rr != -ESRCH)
+ printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr);
+
+ kfree(cn_reply);
+ module_put(THIS_MODULE);
+ return;
+ fail:
+ drbd_nl_send_reply(req, retcode);
+ module_put(THIS_MODULE);
+}
+
+static atomic_t drbd_nl_seq = ATOMIC_INIT(2); /* two. */
+
+static unsigned short *
+__tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data,
+ unsigned short len, int nul_terminated)
+{
+ unsigned short l = tag_descriptions[tag_number(tag)].max_len;
+ len = (len < l) ? len : l;
+ put_unaligned(tag, tl++);
+ put_unaligned(len, tl++);
+ memcpy(tl, data, len);
+ tl = (unsigned short*)((char*)tl + len);
+ if (nul_terminated)
+ *((char*)tl - 1) = 0;
+ return tl;
+}
+
+static unsigned short *
+tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data, int len)
+{
+ return __tl_add_blob(tl, tag, data, len, 0);
+}
+
+static unsigned short *
+tl_add_str(unsigned short *tl, enum drbd_tags tag, const char *str)
+{
+ return __tl_add_blob(tl, tag, str, strlen(str)+1, 0);
+}
+
+static unsigned short *
+tl_add_int(unsigned short *tl, enum drbd_tags tag, const void *val)
+{
+ put_unaligned(tag, tl++);
+ switch(tag_type(tag)) {
+ case TT_INTEGER:
+ put_unaligned(sizeof(int), tl++);
+ put_unaligned(*(int *)val, (int *)tl++);
+ tl = (unsigned short*)((char*)tl+sizeof(int));
+ break;
+ case TT_INT64:
+ put_unaligned(sizeof(u64), tl++);
+ put_unaligned(*(u64 *)val, (u64 *)tl++);
+ tl = (unsigned short*)((char*)tl+sizeof(u64));
+ break;
+ default:
+ /* someone did something stupid. */
+ ;
+ }
+ return tl;
+}
+
+void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state state)
+{
+ char buffer[sizeof(struct cn_msg)+
+ sizeof(struct drbd_nl_cfg_reply)+
+ sizeof(struct get_state_tag_len_struct)+
+ sizeof(short int)];
+ struct cn_msg *cn_reply = (struct cn_msg *) buffer;
+ struct drbd_nl_cfg_reply *reply =
+ (struct drbd_nl_cfg_reply *)cn_reply->data;
+ unsigned short *tl = reply->tag_list;
+
+ /* dev_warn(DEV, "drbd_bcast_state() got called\n"); */
+
+ tl = get_state_to_tags(mdev, (struct get_state *)&state, tl);
+
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ cn_reply->id.idx = CN_IDX_DRBD;
+ cn_reply->id.val = CN_VAL_DRBD;
+
+ cn_reply->seq = atomic_add_return(1, &drbd_nl_seq);
+ cn_reply->ack = 0; /* not used here. */
+ cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
+ (int)((char *)tl - (char *)reply->tag_list);
+ cn_reply->flags = 0;
+
+ reply->packet_type = P_get_state;
+ reply->minor = mdev_to_minor(mdev);
+ reply->ret_code = NO_ERROR;
+
+ trace_drbd_netlink(cn_reply, 0);
+ cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
+}
+
+void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name)
+{
+ char buffer[sizeof(struct cn_msg)+
+ sizeof(struct drbd_nl_cfg_reply)+
+ sizeof(struct call_helper_tag_len_struct)+
+ sizeof(short int)];
+ struct cn_msg *cn_reply = (struct cn_msg *) buffer;
+ struct drbd_nl_cfg_reply *reply =
+ (struct drbd_nl_cfg_reply *)cn_reply->data;
+ unsigned short *tl = reply->tag_list;
+
+ /* dev_warn(DEV, "drbd_bcast_state() got called\n"); */
+
+ tl = tl_add_str(tl, T_helper, helper_name);
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ cn_reply->id.idx = CN_IDX_DRBD;
+ cn_reply->id.val = CN_VAL_DRBD;
+
+ cn_reply->seq = atomic_add_return(1, &drbd_nl_seq);
+ cn_reply->ack = 0; /* not used here. */
+ cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
+ (int)((char *)tl - (char *)reply->tag_list);
+ cn_reply->flags = 0;
+
+ reply->packet_type = P_call_helper;
+ reply->minor = mdev_to_minor(mdev);
+ reply->ret_code = NO_ERROR;
+
+ trace_drbd_netlink(cn_reply, 0);
+ cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
+}
+
+void drbd_bcast_ee(struct drbd_conf *mdev,
+ const char *reason, const int dgs,
+ const char* seen_hash, const char* calc_hash,
+ const struct drbd_epoch_entry* e)
+{
+ struct cn_msg *cn_reply;
+ struct drbd_nl_cfg_reply *reply;
+ struct bio_vec *bvec;
+ unsigned short *tl;
+ int i;
+
+ if (!e)
+ return;
+ if (!reason || !reason[0])
+ return;
+
+ /* aparently we have to memcpy twice, first to prepare the data for the
+ * struct cn_msg, then within cn_netlink_send from the cn_msg to the
+ * netlink skb. */
+ /* receiver thread context, which is not in the writeout path (of this node),
+ * but may be in the writeout path of the _other_ node.
+ * GFP_NOIO to avoid potential "distributed deadlock". */
+ cn_reply = kmalloc(
+ sizeof(struct cn_msg)+
+ sizeof(struct drbd_nl_cfg_reply)+
+ sizeof(struct dump_ee_tag_len_struct)+
+ sizeof(short int),
+ GFP_NOIO);
+
+ if (!cn_reply) {
+ dev_err(DEV, "could not kmalloc buffer for drbd_bcast_ee, sector %llu, size %u\n",
+ (unsigned long long)e->sector, e->size);
+ return;
+ }
+
+ reply = (struct drbd_nl_cfg_reply*)cn_reply->data;
+ tl = reply->tag_list;
+
+ tl = tl_add_str(tl, T_dump_ee_reason, reason);
+ tl = tl_add_blob(tl, T_seen_digest, seen_hash, dgs);
+ tl = tl_add_blob(tl, T_calc_digest, calc_hash, dgs);
+ tl = tl_add_int(tl, T_ee_sector, &e->sector);
+ tl = tl_add_int(tl, T_ee_block_id, &e->block_id);
+
+ put_unaligned(T_ee_data, tl++);
+ put_unaligned(e->size, tl++);
+
+ __bio_for_each_segment(bvec, e->private_bio, i, 0) {
+ void *d = kmap(bvec->bv_page);
+ memcpy(tl, d + bvec->bv_offset, bvec->bv_len);
+ kunmap(bvec->bv_page);
+ tl=(unsigned short*)((char*)tl + bvec->bv_len);
+ }
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ cn_reply->id.idx = CN_IDX_DRBD;
+ cn_reply->id.val = CN_VAL_DRBD;
+
+ cn_reply->seq = atomic_add_return(1,&drbd_nl_seq);
+ cn_reply->ack = 0; // not used here.
+ cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
+ (int)((char*)tl - (char*)reply->tag_list);
+ cn_reply->flags = 0;
+
+ reply->packet_type = P_dump_ee;
+ reply->minor = mdev_to_minor(mdev);
+ reply->ret_code = NO_ERROR;
+
+ trace_drbd_netlink(cn_reply, 0);
+ cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
+ kfree(cn_reply);
+}
+
+void drbd_bcast_sync_progress(struct drbd_conf *mdev)
+{
+ char buffer[sizeof(struct cn_msg)+
+ sizeof(struct drbd_nl_cfg_reply)+
+ sizeof(struct sync_progress_tag_len_struct)+
+ sizeof(short int)];
+ struct cn_msg *cn_reply = (struct cn_msg *) buffer;
+ struct drbd_nl_cfg_reply *reply =
+ (struct drbd_nl_cfg_reply *)cn_reply->data;
+ unsigned short *tl = reply->tag_list;
+ unsigned long rs_left;
+ unsigned int res;
+
+ /* no local ref, no bitmap, no syncer progress, no broadcast. */
+ if (!get_ldev(mdev))
+ return;
+ drbd_get_syncer_progress(mdev, &rs_left, &res);
+ put_ldev(mdev);
+
+ tl = tl_add_int(tl, T_sync_progress, &res);
+ put_unaligned(TT_END, tl++); /* Close the tag list */
+
+ cn_reply->id.idx = CN_IDX_DRBD;
+ cn_reply->id.val = CN_VAL_DRBD;
+
+ cn_reply->seq = atomic_add_return(1, &drbd_nl_seq);
+ cn_reply->ack = 0; /* not used here. */
+ cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
+ (int)((char *)tl - (char *)reply->tag_list);
+ cn_reply->flags = 0;
+
+ reply->packet_type = P_sync_progress;
+ reply->minor = mdev_to_minor(mdev);
+ reply->ret_code = NO_ERROR;
+
+ trace_drbd_netlink(cn_reply, 0);
+ cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
+}
+
+int __init drbd_nl_init(void)
+{
+ static struct cb_id cn_id_drbd;
+ int err, try=10;
+
+ cn_id_drbd.val = CN_VAL_DRBD;
+ do {
+ cn_id_drbd.idx = cn_idx;
+ err = cn_add_callback(&cn_id_drbd, "cn_drbd", &drbd_connector_callback);
+ if (!err)
+ break;
+ cn_idx = (cn_idx + CN_IDX_STEP);
+ } while (try--);
+
+ if (err) {
+ printk(KERN_ERR "drbd: cn_drbd failed to register\n");
+ return err;
+ }
+
+ return 0;
+}
+
+void drbd_nl_cleanup(void)
+{
+ static struct cb_id cn_id_drbd;
+
+ cn_id_drbd.idx = cn_idx;
+ cn_id_drbd.val = CN_VAL_DRBD;
+
+ cn_del_callback(&cn_id_drbd);
+}
+
+void drbd_nl_send_reply(struct cn_msg *req, int ret_code)
+{
+ char buffer[sizeof(struct cn_msg)+sizeof(struct drbd_nl_cfg_reply)];
+ struct cn_msg *cn_reply = (struct cn_msg *) buffer;
+ struct drbd_nl_cfg_reply *reply =
+ (struct drbd_nl_cfg_reply *)cn_reply->data;
+ int rr;
+
+ cn_reply->id = req->id;
+
+ cn_reply->seq = req->seq;
+ cn_reply->ack = req->ack + 1;
+ cn_reply->len = sizeof(struct drbd_nl_cfg_reply);
+ cn_reply->flags = 0;
+
+ reply->minor = ((struct drbd_nl_cfg_req *)req->data)->drbd_minor;
+ reply->ret_code = ret_code;
+
+ trace_drbd_netlink(cn_reply, 0);
+ rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
+ if (rr && rr != -ESRCH)
+ printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr);
+}
+
More information about the drbd-dev
mailing list