diff options
Diffstat (limited to 'fs')
69 files changed, 1397 insertions, 1062 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 2bc7ad775842..3ef62bad8f2b 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -79,6 +79,7 @@ config EXPORTFS_BLOCK_OPS config FILE_LOCKING bool "Enable POSIX file locking API" if EXPERT default y + select PERCPU_RWSEM help This option enables standard file locking support, required for filesystems like NFS and for the flock() system diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 7ef637d7f3a5..1e9d2f84e5b5 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -461,8 +461,8 @@ static void afs_callback_updater(struct work_struct *work) */ int __init afs_callback_update_init(void) { - afs_callback_update_worker = - create_singlethread_workqueue("kafs_callbackd"); + afs_callback_update_worker = alloc_ordered_workqueue("kafs_callbackd", + WQ_MEM_RECLAIM); return afs_callback_update_worker ? 0 : -ENOMEM; } diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 85737e96ab8b..2037e7a77a37 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -17,19 +17,12 @@ #include "internal.h" #include "afs_cm.h" -#if 0 -struct workqueue_struct *afs_cm_workqueue; -#endif /* 0 */ - -static int afs_deliver_cb_init_call_back_state(struct afs_call *, - struct sk_buff *, bool); -static int afs_deliver_cb_init_call_back_state3(struct afs_call *, - struct sk_buff *, bool); -static int afs_deliver_cb_probe(struct afs_call *, struct sk_buff *, bool); -static int afs_deliver_cb_callback(struct afs_call *, struct sk_buff *, bool); -static int afs_deliver_cb_probe_uuid(struct afs_call *, struct sk_buff *, bool); -static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *, - struct sk_buff *, bool); +static int afs_deliver_cb_init_call_back_state(struct afs_call *); +static int afs_deliver_cb_init_call_back_state3(struct afs_call *); +static int afs_deliver_cb_probe(struct afs_call *); +static int afs_deliver_cb_callback(struct afs_call *); +static int afs_deliver_cb_probe_uuid(struct afs_call *); +static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *); static void afs_cm_destructor(struct afs_call *); /* @@ -134,7 +127,7 @@ static void afs_cm_destructor(struct afs_call *call) * received. The step number here must match the final number in * afs_deliver_cb_callback(). */ - if (call->unmarshall == 6) { + if (call->unmarshall == 5) { ASSERT(call->server && call->count && call->request); afs_break_callbacks(call->server, call->count, call->request); } @@ -168,27 +161,27 @@ static void SRXAFSCB_CallBack(struct work_struct *work) /* * deliver request data to a CB.CallBack call */ -static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, - bool last) +static int afs_deliver_cb_callback(struct afs_call *call) { + struct sockaddr_rxrpc srx; struct afs_callback *cb; struct afs_server *server; - struct in_addr addr; __be32 *bp; u32 tmp; int ret, loop; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); switch (call->unmarshall) { case 0: + rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx); call->offset = 0; call->unmarshall++; /* extract the FID array and its count in two steps */ case 1: _debug("extract FID count"); - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -205,8 +198,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, case 2: _debug("extract FID array"); - ret = afs_extract_data(call, skb, last, call->buffer, - call->count * 3 * 4); + ret = afs_extract_data(call, call->buffer, + call->count * 3 * 4, true); if (ret < 0) return ret; @@ -232,7 +225,7 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, /* extract the callback array and its count in two steps */ case 3: _debug("extract CB count"); - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -242,13 +235,11 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, return -EBADMSG; call->offset = 0; call->unmarshall++; - if (tmp == 0) - goto empty_cb_array; case 4: _debug("extract CB array"); - ret = afs_extract_data(call, skb, last, call->request, - call->count * 3 * 4); + ret = afs_extract_data(call, call->buffer, + call->count * 3 * 4, false); if (ret < 0) return ret; @@ -261,15 +252,9 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, cb->type = ntohl(*bp++); } - empty_cb_array: call->offset = 0; call->unmarshall++; - case 5: - ret = afs_data_complete(call, skb, last); - if (ret < 0) - return ret; - /* Record that the message was unmarshalled successfully so * that the call destructor can know do the callback breaking * work, even if the final ACK isn't received. @@ -278,17 +263,15 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, * updated also. */ call->unmarshall++; - case 6: + case 5: break; } - call->state = AFS_CALL_REPLYING; /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - memcpy(&addr, &ip_hdr(skb)->saddr, 4); - server = afs_find_server(&addr); + server = afs_find_server(&srx); if (!server) return -ENOTCONN; call->server = server; @@ -315,17 +298,17 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) /* * deliver request data to a CB.InitCallBackState call */ -static int afs_deliver_cb_init_call_back_state(struct afs_call *call, - struct sk_buff *skb, - bool last) +static int afs_deliver_cb_init_call_back_state(struct afs_call *call) { + struct sockaddr_rxrpc srx; struct afs_server *server; - struct in_addr addr; int ret; - _enter(",{%u},%d", skb->len, last); + _enter(""); + + rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx); - ret = afs_data_complete(call, skb, last); + ret = afs_extract_data(call, NULL, 0, false); if (ret < 0) return ret; @@ -334,8 +317,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call, /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - memcpy(&addr, &ip_hdr(skb)->saddr, 4); - server = afs_find_server(&addr); + server = afs_find_server(&srx); if (!server) return -ENOTCONN; call->server = server; @@ -348,27 +330,68 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call, /* * deliver request data to a CB.InitCallBackState3 call */ -static int afs_deliver_cb_init_call_back_state3(struct afs_call *call, - struct sk_buff *skb, - bool last) +static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) { + struct sockaddr_rxrpc srx; struct afs_server *server; - struct in_addr addr; + struct afs_uuid *r; + unsigned loop; + __be32 *b; + int ret; + + _enter(""); + + rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx); + + _enter("{%u}", call->unmarshall); - _enter(",{%u},%d", skb->len, last); + switch (call->unmarshall) { + case 0: + call->offset = 0; + call->buffer = kmalloc(11 * sizeof(__be32), GFP_KERNEL); + if (!call->buffer) + return -ENOMEM; + call->unmarshall++; - /* There are some arguments that we ignore */ - afs_data_consumed(call, skb); - if (!last) - return -EAGAIN; + case 1: + _debug("extract UUID"); + ret = afs_extract_data(call, call->buffer, + 11 * sizeof(__be32), false); + switch (ret) { + case 0: break; + case -EAGAIN: return 0; + default: return ret; + } + + _debug("unmarshall UUID"); + call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); + if (!call->request) + return -ENOMEM; + + b = call->buffer; + r = call->request; + r->time_low = ntohl(b[0]); + r->time_mid = ntohl(b[1]); + r->time_hi_and_version = ntohl(b[2]); + r->clock_seq_hi_and_reserved = ntohl(b[3]); + r->clock_seq_low = ntohl(b[4]); + + for (loop = 0; loop < 6; loop++) + r->node[loop] = ntohl(b[loop + 5]); + + call->offset = 0; + call->unmarshall++; + + case 2: + break; + } /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - memcpy(&addr, &ip_hdr(skb)->saddr, 4); - server = afs_find_server(&addr); + server = afs_find_server(&srx); if (!server) return -ENOTCONN; call->server = server; @@ -393,14 +416,13 @@ static void SRXAFSCB_Probe(struct work_struct *work) /* * deliver request data to a CB.Probe call */ -static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb, - bool last) +static int afs_deliver_cb_probe(struct afs_call *call) { int ret; - _enter(",{%u},%d", skb->len, last); + _enter(""); - ret = afs_data_complete(call, skb, last); + ret = afs_extract_data(call, NULL, 0, false); if (ret < 0) return ret; @@ -426,7 +448,6 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) _enter(""); - if (memcmp(r, &afs_uuid, sizeof(afs_uuid)) == 0) reply.match = htonl(0); else @@ -439,19 +460,14 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) /* * deliver request data to a CB.ProbeUuid call */ -static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, - bool last) +static int afs_deliver_cb_probe_uuid(struct afs_call *call) { struct afs_uuid *r; unsigned loop; __be32 *b; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - - ret = afs_data_complete(call, skb, last); - if (ret < 0) - return ret; + _enter("{%u}", call->unmarshall); switch (call->unmarshall) { case 0: @@ -463,8 +479,8 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, case 1: _debug("extract UUID"); - ret = afs_extract_data(call, skb, last, call->buffer, - 11 * sizeof(__be32)); + ret = afs_extract_data(call, call->buffer, + 11 * sizeof(__be32), false); switch (ret) { case 0: break; case -EAGAIN: return 0; @@ -491,16 +507,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, call->unmarshall++; case 2: - _debug("trailer"); - if (skb->len != 0) - return -EBADMSG; break; } - ret = afs_data_complete(call, skb, last); - if (ret < 0) - return ret; - call->state = AFS_CALL_REPLYING; INIT_WORK(&call->work, SRXAFSCB_ProbeUuid); @@ -574,14 +583,13 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) /* * deliver request data to a CB.TellMeAboutYourself call */ -static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call) { int ret; - _enter(",{%u},%d", skb->len, last); + _enter(""); - ret = afs_data_complete(call, skb, last); + ret = afs_extract_data(call, NULL, 0, false); if (ret < 0) return ret; diff --git a/fs/afs/flock.c b/fs/afs/flock.c index d91a9c9cfbd0..3191dff2c156 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -36,8 +36,8 @@ static int afs_init_lock_manager(void) if (!afs_lock_manager) { mutex_lock(&afs_lock_manager_mutex); if (!afs_lock_manager) { - afs_lock_manager = - create_singlethread_workqueue("kafs_lockd"); + afs_lock_manager = alloc_workqueue("kafs_lockd", + WQ_MEM_RECLAIM, 0); if (!afs_lock_manager) ret = -ENOMEM; } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 9312b92e54be..96f4d764d1a6 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -235,16 +235,15 @@ static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp, /* * deliver reply data to an FS.FetchStatus */ -static int afs_deliver_fs_fetch_status(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_fetch_status(struct afs_call *call) { struct afs_vnode *vnode = call->reply; const __be32 *bp; int ret; - _enter(",,%u", last); + _enter(""); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -307,8 +306,7 @@ int afs_fs_fetch_file_status(struct afs_server *server, /* * deliver reply data to an FS.FetchData */ -static int afs_deliver_fs_fetch_data(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_fetch_data(struct afs_call *call) { struct afs_vnode *vnode = call->reply; const __be32 *bp; @@ -316,7 +314,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, void *buffer; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); switch (call->unmarshall) { case 0: @@ -332,7 +330,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, * client) */ case 1: _debug("extract data length (MSW)"); - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -347,7 +345,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, /* extract the returned data length */ case 2: _debug("extract data length"); - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -363,10 +361,10 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, _debug("extract data"); if (call->count > 0) { page = call->reply3; - buffer = kmap_atomic(page); - ret = afs_extract_data(call, skb, last, buffer, - call->count); - kunmap_atomic(buffer); + buffer = kmap(page); + ret = afs_extract_data(call, buffer, + call->count, true); + kunmap(buffer); if (ret < 0) return ret; } @@ -376,8 +374,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, /* extract the metadata */ case 4: - ret = afs_extract_data(call, skb, last, call->buffer, - (21 + 3 + 6) * 4); + ret = afs_extract_data(call, call->buffer, + (21 + 3 + 6) * 4, false); if (ret < 0) return ret; @@ -391,18 +389,15 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, call->unmarshall++; case 5: - ret = afs_data_complete(call, skb, last); - if (ret < 0) - return ret; break; } if (call->count < PAGE_SIZE) { _debug("clear"); page = call->reply3; - buffer = kmap_atomic(page); + buffer = kmap(page); memset(buffer + call->count, 0, PAGE_SIZE - call->count); - kunmap_atomic(buffer); + kunmap(buffer); } _leave(" = 0 [done]"); @@ -515,13 +510,12 @@ int afs_fs_fetch_data(struct afs_server *server, /* * deliver reply data to an FS.GiveUpCallBacks */ -static int afs_deliver_fs_give_up_callbacks(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_give_up_callbacks(struct afs_call *call) { - _enter(",{%u},%d", skb->len, last); + _enter(""); /* shouldn't be any reply data */ - return afs_data_complete(call, skb, last); + return afs_extract_data(call, NULL, 0, false); } /* @@ -599,16 +593,15 @@ int afs_fs_give_up_callbacks(struct afs_server *server, /* * deliver reply data to an FS.CreateFile or an FS.MakeDir */ -static int afs_deliver_fs_create_vnode(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_create_vnode(struct afs_call *call) { struct afs_vnode *vnode = call->reply; const __be32 *bp; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -696,16 +689,15 @@ int afs_fs_create(struct afs_server *server, /* * deliver reply data to an FS.RemoveFile or FS.RemoveDir */ -static int afs_deliver_fs_remove(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_remove(struct afs_call *call) { struct afs_vnode *vnode = call->reply; const __be32 *bp; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -777,16 +769,15 @@ int afs_fs_remove(struct afs_server *server, /* * deliver reply data to an FS.Link */ -static int afs_deliver_fs_link(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_link(struct afs_call *call) { struct afs_vnode *dvnode = call->reply, *vnode = call->reply2; const __be32 *bp; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -863,16 +854,15 @@ int afs_fs_link(struct afs_server *server, /* * deliver reply data to an FS.Symlink */ -static int afs_deliver_fs_symlink(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_symlink(struct afs_call *call) { struct afs_vnode *vnode = call->reply; const __be32 *bp; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -968,16 +958,15 @@ int afs_fs_symlink(struct afs_server *server, /* * deliver reply data to an FS.Rename */ -static int afs_deliver_fs_rename(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_rename(struct afs_call *call) { struct afs_vnode *orig_dvnode = call->reply, *new_dvnode = call->reply2; const __be32 *bp; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -1072,16 +1061,15 @@ int afs_fs_rename(struct afs_server *server, /* * deliver reply data to an FS.StoreData */ -static int afs_deliver_fs_store_data(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_store_data(struct afs_call *call) { struct afs_vnode *vnode = call->reply; const __be32 *bp; int ret; - _enter(",,%u", last); + _enter(""); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -1251,17 +1239,16 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, /* * deliver reply data to an FS.StoreStatus */ -static int afs_deliver_fs_store_status(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_store_status(struct afs_call *call) { afs_dataversion_t *store_version; struct afs_vnode *vnode = call->reply; const __be32 *bp; int ret; - _enter(",,%u", last); + _enter(""); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; @@ -1443,14 +1430,13 @@ int afs_fs_setattr(struct afs_server *server, struct key *key, /* * deliver reply data to an FS.GetVolumeStatus */ -static int afs_deliver_fs_get_volume_status(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_get_volume_status(struct afs_call *call) { const __be32 *bp; char *p; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); switch (call->unmarshall) { case 0: @@ -1460,8 +1446,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the returned status record */ case 1: _debug("extract status"); - ret = afs_extract_data(call, skb, last, call->buffer, - 12 * 4); + ret = afs_extract_data(call, call->buffer, + 12 * 4, true); if (ret < 0) return ret; @@ -1472,7 +1458,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the volume name length */ case 2: - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -1487,8 +1473,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 3: _debug("extract volname"); if (call->count > 0) { - ret = afs_extract_data(call, skb, last, call->reply3, - call->count); + ret = afs_extract_data(call, call->reply3, + call->count, true); if (ret < 0) return ret; } @@ -1508,8 +1494,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, call->count = 4 - (call->count & 3); case 4: - ret = afs_extract_data(call, skb, last, call->buffer, - call->count); + ret = afs_extract_data(call, call->buffer, + call->count, true); if (ret < 0) return ret; @@ -1519,7 +1505,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the offline message length */ case 5: - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -1534,8 +1520,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 6: _debug("extract offline"); if (call->count > 0) { - ret = afs_extract_data(call, skb, last, call->reply3, - call->count); + ret = afs_extract_data(call, call->reply3, + call->count, true); if (ret < 0) return ret; } @@ -1555,8 +1541,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, call->count = 4 - (call->count & 3); case 7: - ret = afs_extract_data(call, skb, last, call->buffer, - call->count); + ret = afs_extract_data(call, call->buffer, + call->count, true); if (ret < 0) return ret; @@ -1566,7 +1552,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the message of the day length */ case 8: - ret = afs_extract_data(call, skb, last, &call->tmp, 4); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; @@ -1581,8 +1567,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 9: _debug("extract motd"); if (call->count > 0) { - ret = afs_extract_data(call, skb, last, call->reply3, - call->count); + ret = afs_extract_data(call, call->reply3, + call->count, true); if (ret < 0) return ret; } @@ -1595,26 +1581,17 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, call->unmarshall++; /* extract the message of the day padding */ - if ((call->count & 3) == 0) { - call->unmarshall++; - goto no_motd_padding; - } - call->count = 4 - (call->count & 3); + call->count = (4 - (call->count & 3)) & 3; case 10: - ret = afs_extract_data(call, skb, last, call->buffer, - call->count); + ret = afs_extract_data(call, call->buffer, + call->count, false); if (ret < 0) return ret; call->offset = 0; call->unmarshall++; - no_motd_padding: - case 11: - ret = afs_data_complete(call, skb, last); - if (ret < 0) - return ret; break; } @@ -1685,15 +1662,14 @@ int afs_fs_get_volume_status(struct afs_server *server, /* * deliver reply data to an FS.SetLock, FS.ExtendLock or FS.ReleaseLock */ -static int afs_deliver_fs_xxxx_lock(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_fs_xxxx_lock(struct afs_call *call) { const __be32 *bp; int ret; - _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); + _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index df976b2a7f40..5497c8496055 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -13,13 +13,13 @@ #include <linux/kernel.h> #include <linux/fs.h> #include <linux/pagemap.h> -#include <linux/skbuff.h> #include <linux/rxrpc.h> #include <linux/key.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/fscache.h> #include <linux/backing-dev.h> +#include <net/af_rxrpc.h> #include "afs.h" #include "afs_vl.h" @@ -56,7 +56,7 @@ struct afs_mount_params { */ struct afs_wait_mode { /* RxRPC received message notification */ - void (*rx_wakeup)(struct afs_call *call); + rxrpc_notify_rx_t notify_rx; /* synchronous call waiter and call dispatched notification */ int (*wait)(struct afs_call *call); @@ -75,10 +75,8 @@ struct afs_call { const struct afs_call_type *type; /* type of call */ const struct afs_wait_mode *wait_mode; /* completion wait mode */ wait_queue_head_t waitq; /* processes awaiting completion */ - void (*async_workfn)(struct afs_call *call); /* asynchronous work function */ struct work_struct async_work; /* asynchronous work processor */ struct work_struct work; /* actual work processor */ - struct sk_buff_head rx_queue; /* received packets */ struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ struct afs_server *server; /* server affected by incoming CM call */ @@ -92,6 +90,7 @@ struct afs_call { void *reply4; /* reply buffer (fourth part) */ pgoff_t first; /* first page in mapping to deal with */ pgoff_t last; /* last page in mapping to deal with */ + size_t offset; /* offset into received data store */ enum { /* call state */ AFS_CALL_REQUESTING, /* request is being sent for outgoing call */ AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */ @@ -99,21 +98,18 @@ struct afs_call { AFS_CALL_AWAIT_REQUEST, /* awaiting request data on incoming call */ AFS_CALL_REPLYING, /* replying to incoming call */ AFS_CALL_AWAIT_ACK, /* awaiting final ACK of incoming call */ - AFS_CALL_COMPLETE, /* successfully completed */ - AFS_CALL_BUSY, /* server was busy */ - AFS_CALL_ABORTED, /* call was aborted */ - AFS_CALL_ERROR, /* call failed due to error */ + AFS_CALL_COMPLETE, /* Completed or failed */ } state; int error; /* error code */ + u32 abort_code; /* Remote abort ID or 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ - unsigned reply_size; /* current size of reply */ unsigned first_offset; /* offset into mapping[first] */ unsigned last_to; /* amount of mapping[last] */ - unsigned offset; /* offset into received data store */ unsigned char unmarshall; /* unmarshalling phase */ bool incoming; /* T if incoming call */ bool send_pages; /* T if data from mapping should be sent */ + bool need_attention; /* T if RxRPC poked us */ u16 service_id; /* RxRPC service ID to call */ __be16 port; /* target UDP port */ __be32 operation_ID; /* operation ID for an incoming call */ @@ -128,8 +124,7 @@ struct afs_call_type { /* deliver request or reply data to an call * - returning an error will cause the call to be aborted */ - int (*deliver)(struct afs_call *call, struct sk_buff *skb, - bool last); + int (*deliver)(struct afs_call *call); /* map an abort code to an error number */ int (*abort_to_error)(u32 abort_code); @@ -607,29 +602,22 @@ extern void afs_proc_cell_remove(struct afs_cell *); /* * rxrpc.c */ +extern struct socket *afs_socket; + extern int afs_open_socket(void); extern void afs_close_socket(void); -extern void afs_data_consumed(struct afs_call *, struct sk_buff *); extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, const struct afs_wait_mode *); extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *, size_t, size_t); extern void afs_flat_call_destructor(struct afs_call *); -extern int afs_transfer_reply(struct afs_call *, struct sk_buff *, bool); extern void afs_send_empty_reply(struct afs_call *); extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); -extern int afs_extract_data(struct afs_call *, struct sk_buff *, bool, void *, - size_t); +extern int afs_extract_data(struct afs_call *, void *, size_t, bool); -static inline int afs_data_complete(struct afs_call *call, struct sk_buff *skb, - bool last) +static inline int afs_transfer_reply(struct afs_call *call) { - if (skb->len > 0) - return -EBADMSG; - afs_data_consumed(call, skb); - if (!last) - return -EAGAIN; - return 0; + return afs_extract_data(call, call->buffer, call->reply_max, false); } /* @@ -654,7 +642,7 @@ do { \ extern struct afs_server *afs_lookup_server(struct afs_cell *, const struct in_addr *); -extern struct afs_server *afs_find_server(const struct in_addr *); +extern struct afs_server *afs_find_server(const struct sockaddr_rxrpc *); extern void afs_put_server(struct afs_server *); extern void __exit afs_purge_servers(void); diff --git a/fs/afs/main.c b/fs/afs/main.c index 35de0c04729f..0b187ef3b5b7 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/completion.h> #include <linux/sched.h> +#include <linux/random.h> #include "internal.h" MODULE_DESCRIPTION("AFS Client File System"); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 14d04c848465..59bdaa7527b6 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -16,34 +16,36 @@ #include "internal.h" #include "afs_cm.h" -static struct socket *afs_socket; /* my RxRPC socket */ +struct socket *afs_socket; /* my RxRPC socket */ static struct workqueue_struct *afs_async_calls; +static struct afs_call *afs_spare_incoming_call; static atomic_t afs_outstanding_calls; -static atomic_t afs_outstanding_skbs; -static void afs_wake_up_call_waiter(struct afs_call *); +static void afs_free_call(struct afs_call *); +static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long); static int afs_wait_for_call_to_complete(struct afs_call *); -static void afs_wake_up_async_call(struct afs_call *); +static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long); static int afs_dont_wait_for_call_to_complete(struct afs_call *); -static void afs_process_async_call(struct afs_call *); -static void afs_rx_interceptor(struct sock *, unsigned long, struct sk_buff *); -static int afs_deliver_cm_op_id(struct afs_call *, struct sk_buff *, bool); +static void afs_process_async_call(struct work_struct *); +static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long); +static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long); +static int afs_deliver_cm_op_id(struct afs_call *); /* synchronous call management */ const struct afs_wait_mode afs_sync_call = { - .rx_wakeup = afs_wake_up_call_waiter, + .notify_rx = afs_wake_up_call_waiter, .wait = afs_wait_for_call_to_complete, }; /* asynchronous call management */ const struct afs_wait_mode afs_async_call = { - .rx_wakeup = afs_wake_up_async_call, + .notify_rx = afs_wake_up_async_call, .wait = afs_dont_wait_for_call_to_complete, }; /* asynchronous incoming call management */ static const struct afs_wait_mode afs_async_incoming_call = { - .rx_wakeup = afs_wake_up_async_call, + .notify_rx = afs_wake_up_async_call, }; /* asynchronous incoming call initial processing */ @@ -53,17 +55,9 @@ static const struct afs_call_type afs_RXCMxxxx = { .abort_to_error = afs_abort_to_error, }; -static void afs_collect_incoming_call(struct work_struct *); +static void afs_charge_preallocation(struct work_struct *); -static struct sk_buff_head afs_incoming_calls; -static DECLARE_WORK(afs_collect_incoming_call_work, afs_collect_incoming_call); - -static void afs_async_workfn(struct work_struct *work) -{ - struct afs_call *call = container_of(work, struct afs_call, async_work); - - call->async_workfn(call); -} +static DECLARE_WORK(afs_charge_preallocation_work, afs_charge_preallocation); static int afs_wait_atomic_t(atomic_t *p) { @@ -83,10 +77,8 @@ int afs_open_socket(void) _enter(""); - skb_queue_head_init(&afs_incoming_calls); - ret = -ENOMEM; - afs_async_calls = create_singlethread_workqueue("kafsd"); + afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0); if (!afs_async_calls) goto error_0; @@ -110,13 +102,15 @@ int afs_open_socket(void) if (ret < 0) goto error_2; + rxrpc_kernel_new_call_notification(socket, afs_rx_new_call, + afs_rx_discard_new_call); + ret = kernel_listen(socket, INT_MAX); if (ret < 0) goto error_2; - rxrpc_kernel_intercept_rx_messages(socket, afs_rx_interceptor); - afs_socket = socket; + afs_charge_preallocation(NULL); _leave(" = 0"); return 0; @@ -136,52 +130,28 @@ void afs_close_socket(void) { _enter(""); + if (afs_spare_incoming_call) { + atomic_inc(&afs_outstanding_calls); + afs_free_call(afs_spare_incoming_call); + afs_spare_incoming_call = NULL; + } + + _debug("outstanding %u", atomic_read(&afs_outstanding_calls)); wait_on_atomic_t(&afs_outstanding_calls, afs_wait_atomic_t, TASK_UNINTERRUPTIBLE); _debug("no outstanding calls"); + flush_workqueue(afs_async_calls); + kernel_sock_shutdown(afs_socket, SHUT_RDWR); + flush_workqueue(afs_async_calls); sock_release(afs_socket); _debug("dework"); destroy_workqueue(afs_async_calls); - - ASSERTCMP(atomic_read(&afs_outstanding_skbs), ==, 0); _leave(""); } /* - * Note that the data in a socket buffer is now consumed. - */ -void afs_data_consumed(struct afs_call *call, struct sk_buff *skb) -{ - if (!skb) { - _debug("DLVR NULL [%d]", atomic_read(&afs_outstanding_skbs)); - dump_stack(); - } else { - _debug("DLVR %p{%u} [%d]", - skb, skb->mark, atomic_read(&afs_outstanding_skbs)); - rxrpc_kernel_data_consumed(call->rxcall, skb); - } -} - -/* - * free a socket buffer - */ -static void afs_free_skb(struct sk_buff *skb) -{ - if (!skb) { - _debug("FREE NULL [%d]", atomic_read(&afs_outstanding_skbs)); - dump_stack(); - } else { - _debug("FREE %p{%u} [%d]", - skb, skb->mark, atomic_read(&afs_outstanding_skbs)); - if (atomic_dec_return(&afs_outstanding_skbs) == -1) - BUG(); - rxrpc_kernel_free_skb(skb); - } -} - -/* * free a call */ static void afs_free_call(struct afs_call *call) @@ -191,7 +161,6 @@ static void afs_free_call(struct afs_call *call) ASSERTCMP(call->rxcall, ==, NULL); ASSERT(!work_pending(&call->async_work)); - ASSERT(skb_queue_empty(&call->rx_queue)); ASSERT(call->type->name != NULL); kfree(call->request); @@ -207,7 +176,7 @@ static void afs_free_call(struct afs_call *call) static void afs_end_call_nofree(struct afs_call *call) { if (call->rxcall) { - rxrpc_kernel_end_call(call->rxcall); + rxrpc_kernel_end_call(afs_socket, call->rxcall); call->rxcall = NULL; } if (call->type->destructor) @@ -227,7 +196,7 @@ static void afs_end_call(struct afs_call *call) * allocate a call with flat request and reply buffers */ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, - size_t request_size, size_t reply_size) + size_t request_size, size_t reply_max) { struct afs_call *call; @@ -241,7 +210,7 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, call->type = type; call->request_size = request_size; - call->reply_max = reply_size; + call->reply_max = reply_max; if (request_size) { call->request = kmalloc(request_size, GFP_NOFS); @@ -249,14 +218,13 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, goto nomem_free; } - if (reply_size) { - call->buffer = kmalloc(reply_size, GFP_NOFS); + if (reply_max) { + call->buffer = kmalloc(reply_max, GFP_NOFS); if (!call->buffer) goto nomem_free; } init_waitqueue_head(&call->waitq); - skb_queue_head_init(&call->rx_queue); return call; nomem_free: @@ -325,8 +293,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, * returns from sending the request */ if (first + loop >= last) call->state = AFS_CALL_AWAIT_REPLY; - ret = rxrpc_kernel_send_data(call->rxcall, msg, - to - offset); + ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, + msg, to - offset); kunmap(pages[loop]); if (ret < 0) break; @@ -354,7 +322,6 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, struct msghdr msg; struct kvec iov[1]; int ret; - struct sk_buff *skb; _enter("%x,{%d},", addr->s_addr, ntohs(call->port)); @@ -366,8 +333,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, atomic_read(&afs_outstanding_calls)); call->wait_mode = wait_mode; - call->async_workfn = afs_process_async_call; - INIT_WORK(&call->async_work, afs_async_workfn); + INIT_WORK(&call->async_work, afs_process_async_call); memset(&srx, 0, sizeof(srx)); srx.srx_family = AF_RXRPC; @@ -380,7 +346,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, /* create a call */ rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key, - (unsigned long) call, gfp); + (unsigned long) call, gfp, + wait_mode->notify_rx); call->key = NULL; if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); @@ -406,7 +373,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, * request */ if (!call->send_pages) call->state = AFS_CALL_AWAIT_REPLY; - ret = rxrpc_kernel_send_data(rxcall, &msg, call->request_size); + ret = rxrpc_kernel_send_data(afs_socket, rxcall, + &msg, call->request_size); if (ret < 0) goto error_do_abort; @@ -421,9 +389,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, return wait_mode->wait(call); error_do_abort: - rxrpc_kernel_abort_call(rxcall, RX_USER_ABORT); - while ((skb = skb_dequeue(&call->rx_queue))) - afs_free_skb(skb); + rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD"); error_kill_call: afs_end_call(call); _leave(" = %d", ret); @@ -431,140 +397,77 @@ error_kill_call: } /* - * Handles intercepted messages that were arriving in the socket's Rx queue. - * - * Called from the AF_RXRPC call processor in waitqueue process context. For - * each call, it is guaranteed this will be called in order of packet to be - * delivered. - */ -static void afs_rx_interceptor(struct sock *sk, unsigned long user_call_ID, - struct sk_buff *skb) -{ - struct afs_call *call = (struct afs_call *) user_call_ID; - - _enter("%p,,%u", call, skb->mark); - - _debug("ICPT %p{%u} [%d]", - skb, skb->mark, atomic_read(&afs_outstanding_skbs)); - - ASSERTCMP(sk, ==, afs_socket->sk); - atomic_inc(&afs_outstanding_skbs); - - if (!call) { - /* its an incoming call for our callback service */ - skb_queue_tail(&afs_incoming_calls, skb); - queue_work(afs_wq, &afs_collect_incoming_call_work); - } else { - /* route the messages directly to the appropriate call */ - skb_queue_tail(&call->rx_queue, skb); - call->wait_mode->rx_wakeup(call); - } - - _leave(""); -} - -/* * deliver messages to a call */ static void afs_deliver_to_call(struct afs_call *call) { - struct sk_buff *skb; - bool last; u32 abort_code; int ret; - _enter(""); - - while ((call->state == AFS_CALL_AWAIT_REPLY || - call->state == AFS_CALL_AWAIT_OP_ID || - call->state == AFS_CALL_AWAIT_REQUEST || - call->state == AFS_CALL_AWAIT_ACK) && - (skb = skb_dequeue(&call->rx_queue))) { - switch (skb->mark) { - case RXRPC_SKB_MARK_DATA: - _debug("Rcv DATA"); - last = rxrpc_kernel_is_data_last(skb); - ret = call->type->deliver(call, skb, last); - switch (ret) { - case -EAGAIN: - if (last) { - _debug("short data"); - goto unmarshal_error; - } - break; - case 0: - ASSERT(last); - if (call->state == AFS_CALL_AWAIT_REPLY) - call->state = AFS_CALL_COMPLETE; - break; - case -ENOTCONN: - abort_code = RX_CALL_DEAD; - goto do_abort; - case -ENOTSUPP: - abort_code = RX_INVALID_OPERATION; - goto do_abort; - default: - unmarshal_error: - abort_code = RXGEN_CC_UNMARSHAL; - if (call->state != AFS_CALL_AWAIT_REPLY) - abort_code = RXGEN_SS_UNMARSHAL; - do_abort: - rxrpc_kernel_abort_call(call->rxcall, - abort_code); - call->error = ret; - call->state = AFS_CALL_ERROR; - break; + _enter("%s", call->type->name); + + while (call->state == AFS_CALL_AWAIT_REPLY || + call->state == AFS_CALL_AWAIT_OP_ID || + call->state == AFS_CALL_AWAIT_REQUEST || + call->state == AFS_CALL_AWAIT_ACK + ) { + if (call->state == AFS_CALL_AWAIT_ACK) { + size_t offset = 0; + ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, + NULL, 0, &offset, false, + &call->abort_code); + if (ret == -EINPROGRESS || ret == -EAGAIN) + return; + if (ret == 1) { + call->state = AFS_CALL_COMPLETE; + goto done; } - break; - case RXRPC_SKB_MARK_FINAL_ACK: - _debug("Rcv ACK"); - call->state = AFS_CALL_COMPLETE; - break; - case RXRPC_SKB_MARK_BUSY: - _debug("Rcv BUSY"); - call->error = -EBUSY; - call->state = AFS_CALL_BUSY; - break; - case RXRPC_SKB_MARK_REMOTE_ABORT: - abort_code = rxrpc_kernel_get_abort_code(skb); - call->error = call->type->abort_to_error(abort_code); - call->state = AFS_CALL_ABORTED; - _debug("Rcv ABORT %u -> %d", abort_code, call->error); - break; - case RXRPC_SKB_MARK_LOCAL_ABORT: - abort_code = rxrpc_kernel_get_abort_code(skb); - call->error = call->type->abort_to_error(abort_code); - call->state = AFS_CALL_ABORTED; - _debug("Loc ABORT %u -> %d", abort_code, call->error); - break; - case RXRPC_SKB_MARK_NET_ERROR: - call->error = -rxrpc_kernel_get_error_number(skb); - call->state = AFS_CALL_ERROR; - _debug("Rcv NET ERROR %d", call->error); - break; - case RXRPC_SKB_MARK_LOCAL_ERROR: - call->error = -rxrpc_kernel_get_error_number(skb); - call->state = AFS_CALL_ERROR; - _debug("Rcv LOCAL ERROR %d", call->error); - break; - default: - BUG(); - break; + return; } - afs_free_skb(skb); - } - - /* make sure the queue is empty if the call is done with (we might have - * aborted the call early because of an unmarshalling error) */ - if (call->state >= AFS_CALL_COMPLETE) { - while ((skb = skb_dequeue(&call->rx_queue))) - afs_free_skb(skb); - if (call->incoming) - afs_end_call(call); + ret = call->type->deliver(call); + switch (ret) { + case 0: + if (call->state == AFS_CALL_AWAIT_REPLY) + call->state = AFS_CALL_COMPLETE; + goto done; + case -EINPROGRESS: + case -EAGAIN: + goto out; + case -ENOTCONN: + abort_code = RX_CALL_DEAD; + rxrpc_kernel_abort_call(afs_socket, call->rxcall, + abort_code, -ret, "KNC"); + goto do_abort; + case -ENOTSUPP: + abort_code = RX_INVALID_OPERATION; + rxrpc_kernel_abort_call(afs_socket, call->rxcall, + abort_code, -ret, "KIV"); + goto do_abort; + case -ENODATA: + case -EBADMSG: + case -EMSGSIZE: + default: + abort_code = RXGEN_CC_UNMARSHAL; + if (call->state != AFS_CALL_AWAIT_REPLY) + abort_code = RXGEN_SS_UNMARSHAL; + rxrpc_kernel_abort_call(afs_socket, call->rxcall, + abort_code, EBADMSG, "KUM"); + goto do_abort; + } } +done: + if (call->state == AFS_CALL_COMPLETE && call->incoming) + afs_end_call(call); +out: _leave(""); + return; + +do_abort: + call->error = ret; + call->state = AFS_CALL_COMPLETE; + goto done; } /* @@ -572,7 +475,7 @@ static void afs_deliver_to_call(struct afs_call *call) */ static int afs_wait_for_call_to_complete(struct afs_call *call) { - struct sk_buff *skb; + const char *abort_why; int ret; DECLARE_WAITQUEUE(myself, current); @@ -584,15 +487,18 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) set_current_state(TASK_INTERRUPTIBLE); /* deliver any messages that are in the queue */ - if (!skb_queue_empty(&call->rx_queue)) { + if (call->state < AFS_CALL_COMPLETE && call->need_attention) { + call->need_attention = false; __set_current_state(TASK_RUNNING); afs_deliver_to_call(call); continue; } + abort_why = "KWC"; ret = call->error; - if (call->state >= AFS_CALL_COMPLETE) + if (call->state == AFS_CALL_COMPLETE) break; + abort_why = "KWI"; ret = -EINTR; if (signal_pending(current)) break; @@ -605,9 +511,8 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) /* kill the call */ if (call->state < AFS_CALL_COMPLETE) { _debug("call incomplete"); - rxrpc_kernel_abort_call(call->rxcall, RX_CALL_DEAD); - while ((skb = skb_dequeue(&call->rx_queue))) - afs_free_skb(skb); + rxrpc_kernel_abort_call(afs_socket, call->rxcall, + RX_CALL_DEAD, -ret, abort_why); } _debug("call complete"); @@ -619,17 +524,24 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) /* * wake up a waiting call */ -static void afs_wake_up_call_waiter(struct afs_call *call) +static void afs_wake_up_call_waiter(struct sock *sk, struct rxrpc_call *rxcall, + unsigned long call_user_ID) { + struct afs_call *call = (struct afs_call *)call_user_ID; + + call->need_attention = true; wake_up(&call->waitq); } /* * wake up an asynchronous call */ -static void afs_wake_up_async_call(struct afs_call *call) +static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, + unsigned long call_user_ID) { - _enter(""); + struct afs_call *call = (struct afs_call *)call_user_ID; + + call->need_attention = true; queue_work(afs_async_calls, &call->async_work); } @@ -647,8 +559,10 @@ static int afs_dont_wait_for_call_to_complete(struct afs_call *call) /* * delete an asynchronous call */ -static void afs_delete_async_call(struct afs_call *call) +static void afs_delete_async_call(struct work_struct *work) { + struct afs_call *call = container_of(work, struct afs_call, async_work); + _enter(""); afs_free_call(call); @@ -658,17 +572,19 @@ static void afs_delete_async_call(struct afs_call *call) /* * perform processing on an asynchronous call - * - on a multiple-thread workqueue this work item may try to run on several - * CPUs at the same time */ -static void afs_process_async_call(struct afs_call *call) +static void afs_process_async_call(struct work_struct *work) { + struct afs_call *call = container_of(work, struct afs_call, async_work); + _enter(""); - if (!skb_queue_empty(&call->rx_queue)) + if (call->state < AFS_CALL_COMPLETE && call->need_attention) { + call->need_attention = false; afs_deliver_to_call(call); + } - if (call->state >= AFS_CALL_COMPLETE && call->wait_mode) { + if (call->state == AFS_CALL_COMPLETE && call->wait_mode) { if (call->wait_mode->async_complete) call->wait_mode->async_complete(call->reply, call->error); @@ -679,122 +595,93 @@ static void afs_process_async_call(struct afs_call *call) /* we can't just delete the call because the work item may be * queued */ - call->async_workfn = afs_delete_async_call; + call->async_work.func = afs_delete_async_call; queue_work(afs_async_calls, &call->async_work); } _leave(""); } -/* - * Empty a socket buffer into a flat reply buffer. - */ -int afs_transfer_reply(struct afs_call *call, struct sk_buff *skb, bool last) +static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID) { - size_t len = skb->len; - - if (len > call->reply_max - call->reply_size) { - _leave(" = -EBADMSG [%zu > %u]", - len, call->reply_max - call->reply_size); - return -EBADMSG; - } + struct afs_call *call = (struct afs_call *)user_call_ID; - if (len > 0) { - if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, - len) < 0) - BUG(); - call->reply_size += len; - } - - afs_data_consumed(call, skb); - if (!last) - return -EAGAIN; - - if (call->reply_size != call->reply_max) { - _leave(" = -EBADMSG [%u != %u]", - call->reply_size, call->reply_max); - return -EBADMSG; - } - return 0; + call->rxcall = rxcall; } /* - * accept the backlog of incoming calls + * Charge the incoming call preallocation. */ -static void afs_collect_incoming_call(struct work_struct *work) +static void afs_charge_preallocation(struct work_struct *work) { - struct rxrpc_call *rxcall; - struct afs_call *call = NULL; - struct sk_buff *skb; - - while ((skb = skb_dequeue(&afs_incoming_calls))) { - _debug("new call"); - - /* don't need the notification */ - afs_free_skb(skb); + struct afs_call *call = afs_spare_incoming_call; + for (;;) { if (!call) { call = kzalloc(sizeof(struct afs_call), GFP_KERNEL); - if (!call) { - rxrpc_kernel_reject_call(afs_socket); - return; - } + if (!call) + break; - call->async_workfn = afs_process_async_call; - INIT_WORK(&call->async_work, afs_async_workfn); + INIT_WORK(&call->async_work, afs_process_async_call); call->wait_mode = &afs_async_incoming_call; call->type = &afs_RXCMxxxx; init_waitqueue_head(&call->waitq); - skb_queue_head_init(&call->rx_queue); call->state = AFS_CALL_AWAIT_OP_ID; - - _debug("CALL %p{%s} [%d]", - call, call->type->name, - atomic_read(&afs_outstanding_calls)); - atomic_inc(&afs_outstanding_calls); } - rxcall = rxrpc_kernel_accept_call(afs_socket, - (unsigned long) call); - if (!IS_ERR(rxcall)) { - call->rxcall = rxcall; - call = NULL; - } + if (rxrpc_kernel_charge_accept(afs_socket, + afs_wake_up_async_call, + afs_rx_attach, + (unsigned long)call, + GFP_KERNEL) < 0) + break; + call = NULL; } + afs_spare_incoming_call = call; +} + +/* + * Discard a preallocated call when a socket is shut down. + */ +static void afs_rx_discard_new_call(struct rxrpc_call *rxcall, + unsigned long user_call_ID) +{ + struct afs_call *call = (struct afs_call *)user_call_ID; - if (call) - afs_free_call(call); + atomic_inc(&afs_outstanding_calls); + call->rxcall = NULL; + afs_free_call(call); +} + +/* + * Notification of an incoming call. + */ +static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall, + unsigned long user_call_ID) +{ + atomic_inc(&afs_outstanding_calls); + queue_work(afs_wq, &afs_charge_preallocation_work); } /* * Grab the operation ID from an incoming cache manager call. The socket * buffer is discarded on error or if we don't yet have sufficient data. */ -static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, - bool last) +static int afs_deliver_cm_op_id(struct afs_call *call) { - size_t len = skb->len; - void *oibuf = (void *) &call->operation_ID; + int ret; - _enter("{%u},{%zu},%d", call->offset, len, last); + _enter("{%zu}", call->offset); ASSERTCMP(call->offset, <, 4); /* the operation ID forms the first four bytes of the request data */ - len = min_t(size_t, len, 4 - call->offset); - if (skb_copy_bits(skb, 0, oibuf + call->offset, len) < 0) - BUG(); - if (!pskb_pull(skb, len)) - BUG(); - call->offset += len; - - if (call->offset < 4) { - afs_data_consumed(call, skb); - _leave(" = -EAGAIN"); - return -EAGAIN; - } + ret = afs_extract_data(call, &call->operation_ID, 4, true); + if (ret < 0) + return ret; call->state = AFS_CALL_AWAIT_REQUEST; + call->offset = 0; /* ask the cache manager to route the call (it'll change the call type * if successful) */ @@ -803,7 +690,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, /* pass responsibility for the remainer of this message off to the * cache manager op */ - return call->type->deliver(call, skb, last); + return call->type->deliver(call); } /* @@ -823,14 +710,15 @@ void afs_send_empty_reply(struct afs_call *call) msg.msg_flags = 0; call->state = AFS_CALL_AWAIT_ACK; - switch (rxrpc_kernel_send_data(call->rxcall, &msg, 0)) { + switch (rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, 0)) { case 0: _leave(" [replied]"); return; case -ENOMEM: _debug("oom"); - rxrpc_kernel_abort_call(call->rxcall, RX_USER_ABORT); + rxrpc_kernel_abort_call(afs_socket, call->rxcall, + RX_USER_ABORT, ENOMEM, "KOO"); default: afs_end_call(call); _leave(" [error]"); @@ -859,7 +747,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) msg.msg_flags = 0; call->state = AFS_CALL_AWAIT_ACK; - n = rxrpc_kernel_send_data(call->rxcall, &msg, len); + n = rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, len); if (n >= 0) { /* Success */ _leave(" [replied]"); @@ -868,7 +756,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) if (n == -ENOMEM) { _debug("oom"); - rxrpc_kernel_abort_call(call->rxcall, RX_USER_ABORT); + rxrpc_kernel_abort_call(afs_socket, call->rxcall, + RX_USER_ABORT, ENOMEM, "KOO"); } afs_end_call(call); _leave(" [error]"); @@ -877,25 +766,40 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) /* * Extract a piece of data from the received data socket buffers. */ -int afs_extract_data(struct afs_call *call, struct sk_buff *skb, - bool last, void *buf, size_t count) +int afs_extract_data(struct afs_call *call, void *buf, size_t count, + bool want_more) { - size_t len = skb->len; + int ret; - _enter("{%u},{%zu},%d,,%zu", call->offset, len, last, count); + _enter("{%s,%zu},,%zu,%d", + call->type->name, call->offset, count, want_more); - ASSERTCMP(call->offset, <, count); + ASSERTCMP(call->offset, <=, count); - len = min_t(size_t, len, count - call->offset); - if (skb_copy_bits(skb, 0, buf + call->offset, len) < 0 || - !pskb_pull(skb, len)) - BUG(); - call->offset += len; + ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, + buf, count, &call->offset, + want_more, &call->abort_code); + if (ret == 0 || ret == -EAGAIN) + return ret; - if (call->offset < count) { - afs_data_consumed(call, skb); - _leave(" = -EAGAIN"); - return -EAGAIN; + if (ret == 1) { + switch (call->state) { + case AFS_CALL_AWAIT_REPLY: + call->state = AFS_CALL_COMPLETE; + break; + case AFS_CALL_AWAIT_REQUEST: + call->state = AFS_CALL_REPLYING; + break; + default: + break; + } + return 0; } - return 0; + + if (ret == -ECONNABORTED) + call->error = call->type->abort_to_error(call->abort_code); + else + call->error = ret; + call->state = AFS_CALL_COMPLETE; + return ret; } diff --git a/fs/afs/server.c b/fs/afs/server.c index f342acf3547d..d4066ab7dd55 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -178,13 +178,18 @@ server_in_two_cells: /* * look up a server by its IP address */ -struct afs_server *afs_find_server(const struct in_addr *_addr) +struct afs_server *afs_find_server(const struct sockaddr_rxrpc *srx) { struct afs_server *server = NULL; struct rb_node *p; - struct in_addr addr = *_addr; + struct in_addr addr = srx->transport.sin.sin_addr; - _enter("%pI4", &addr.s_addr); + _enter("{%d,%pI4}", srx->transport.family, &addr.s_addr); + + if (srx->transport.family != AF_INET) { + WARN(true, "AFS does not yes support non-IPv4 addresses\n"); + return NULL; + } read_lock(&afs_servers_lock); diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index f94d1abdc3eb..94bcd97d22b8 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -58,17 +58,16 @@ static int afs_vl_abort_to_error(u32 abort_code) /* * deliver reply data to a VL.GetEntryByXXX call */ -static int afs_deliver_vl_get_entry_by_xxx(struct afs_call *call, - struct sk_buff *skb, bool last) +static int afs_deliver_vl_get_entry_by_xxx(struct afs_call *call) { struct afs_cache_vlocation *entry; __be32 *bp; u32 tmp; int loop, ret; - _enter(",,%u", last); + _enter(""); - ret = afs_transfer_reply(call, skb, last); + ret = afs_transfer_reply(call); if (ret < 0) return ret; diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 52976785a32c..45a86396fd2d 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -594,8 +594,8 @@ static void afs_vlocation_reaper(struct work_struct *work) */ int __init afs_vlocation_update_init(void) { - afs_vlocation_update_worker = - create_singlethread_workqueue("kafs_vlupdated"); + afs_vlocation_update_worker = alloc_workqueue("kafs_vlupdated", + WQ_MEM_RECLAIM, 0); return afs_vlocation_update_worker ? 0 : -ENOMEM; } diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index b493909e7492..d8e6d421c27f 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -417,6 +417,7 @@ static struct dentry *should_expire(struct dentry *dentry, } return NULL; } + /* * Find an eligible tree to time-out * A tree is eligible if :- @@ -432,6 +433,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, struct dentry *root = sb->s_root; struct dentry *dentry; struct dentry *expired; + struct dentry *found; struct autofs_info *ino; if (!root) @@ -442,31 +444,46 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { + int flags = how; + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(dentry); - if (ino->flags & AUTOFS_INF_WANT_EXPIRE) - expired = NULL; - else - expired = should_expire(dentry, mnt, timeout, how); - if (!expired) { + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); continue; } + spin_unlock(&sbi->fs_lock); + + expired = should_expire(dentry, mnt, timeout, flags); + if (!expired) + continue; + + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(expired); ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); - spin_lock(&sbi->fs_lock); - if (should_expire(expired, mnt, timeout, how)) { - if (expired != dentry) - dput(dentry); - goto found; - } + /* Make sure a reference is not taken on found if + * things have changed. + */ + flags &= ~AUTOFS_EXP_LEAVES; + found = should_expire(expired, mnt, timeout, how); + if (!found || found != expired) + /* Something has changed, continue */ + goto next; + + if (expired != dentry) + dput(dentry); + + spin_lock(&sbi->fs_lock); + goto found; +next: + spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; + spin_unlock(&sbi->fs_lock); if (expired != dentry) dput(expired); - spin_unlock(&sbi->fs_lock); } return NULL; @@ -483,6 +500,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); int status; + int state; /* Block on any pending expire */ if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE)) @@ -490,8 +508,19 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) if (rcu_walk) return -ECHILD; +retry: spin_lock(&sbi->fs_lock); - if (ino->flags & AUTOFS_INF_EXPIRING) { + state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING); + if (state == AUTOFS_INF_WANT_EXPIRE) { + spin_unlock(&sbi->fs_lock); + /* + * Possibly being selected for expire, wait until + * it's selected or not. + */ + schedule_timeout_uninterruptible(HZ/10); + goto retry; + } + if (state & AUTOFS_INF_EXPIRING) { spin_unlock(&sbi->fs_lock); pr_debug("waiting for expire %p name=%pd\n", dentry, dentry); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index e5495f37c6ed..2472af2798c7 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1624,20 +1624,12 @@ static void do_thread_regset_writeback(struct task_struct *task, regset->writeback(task, regset, 1); } -#ifndef PR_REG_SIZE -#define PR_REG_SIZE(S) sizeof(S) -#endif - #ifndef PRSTATUS_SIZE -#define PRSTATUS_SIZE(S) sizeof(S) -#endif - -#ifndef PR_REG_PTR -#define PR_REG_PTR(S) (&((S)->pr_reg)) +#define PRSTATUS_SIZE(S, R) sizeof(S) #endif #ifndef SET_PR_FPVALID -#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V)) +#define SET_PR_FPVALID(S, V, R) ((S)->pr_fpvalid = (V)) #endif static int fill_thread_core_info(struct elf_thread_core_info *t, @@ -1645,6 +1637,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, long signr, size_t *total) { unsigned int i; + unsigned int regset_size = view->regsets[0].n * view->regsets[0].size; /* * NT_PRSTATUS is the one special case, because the regset data @@ -1653,12 +1646,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, * We assume that regset 0 is NT_PRSTATUS. */ fill_prstatus(&t->prstatus, t->task, signr); - (void) view->regsets[0].get(t->task, &view->regsets[0], - 0, PR_REG_SIZE(t->prstatus.pr_reg), - PR_REG_PTR(&t->prstatus), NULL); + (void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset_size, + &t->prstatus.pr_reg, NULL); fill_note(&t->notes[0], "CORE", NT_PRSTATUS, - PRSTATUS_SIZE(t->prstatus), &t->prstatus); + PRSTATUS_SIZE(t->prstatus, regset_size), &t->prstatus); *total += notesize(&t->notes[0]); do_thread_regset_writeback(t->task, &view->regsets[0]); @@ -1688,7 +1680,8 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, regset->core_note_type, size, data); else { - SET_PR_FPVALID(&t->prstatus, 1); + SET_PR_FPVALID(&t->prstatus, + 1, regset_size); fill_note(&t->notes[i], "CORE", NT_PRFPREG, size, data); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 38c2df84cabd..665da8f66ff1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4271,13 +4271,10 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) if (ret < 0) return ret; - /* - * Use new btrfs_qgroup_reserve_data to reserve precious data space - * - * TODO: Find a good method to avoid reserve data space for NOCOW - * range, but don't impact performance on quota disable case. - */ + /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ ret = btrfs_qgroup_reserve_data(inode, start, len); + if (ret) + btrfs_free_reserved_data_space_noquota(inode, start, len); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b2a2da5893af..7fd939bfbd99 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1634,6 +1634,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, int namelen; int ret = 0; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + ret = mnt_want_write_file(file); if (ret) goto out; @@ -1691,6 +1694,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, struct btrfs_ioctl_vol_args *vol_args; int ret; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -1714,6 +1720,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, bool readonly = false; struct btrfs_qgroup_inherit *inherit = NULL; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -2357,6 +2366,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, int ret; int err = 0; + if (!S_ISDIR(dir->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index c30cf49b69d2..2c6312db8516 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -333,6 +333,7 @@ configfs_write_bin_file(struct file *file, const char __user *buf, if (bin_attr->cb_max_size && *ppos + count > bin_attr->cb_max_size) { len = -EFBIG; + goto out; } tbuf = vmalloc(*ppos + count); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 592059f88e04..354e2ab62031 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -97,9 +97,6 @@ EXPORT_SYMBOL_GPL(debugfs_use_file_finish); #define F_DENTRY(filp) ((filp)->f_path.dentry) -#define REAL_FOPS_DEREF(dentry) \ - ((const struct file_operations *)(dentry)->d_fsdata) - static int open_proxy_open(struct inode *inode, struct file *filp) { const struct dentry *dentry = F_DENTRY(filp); @@ -112,7 +109,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) goto out; } - real_fops = REAL_FOPS_DEREF(dentry); + real_fops = debugfs_real_fops(filp); real_fops = fops_get(real_fops); if (!real_fops) { /* Huh? Module did not clean up after itself at exit? */ @@ -143,7 +140,7 @@ static ret_type full_proxy_ ## name(proto) \ { \ const struct dentry *dentry = F_DENTRY(filp); \ const struct file_operations *real_fops = \ - REAL_FOPS_DEREF(dentry); \ + debugfs_real_fops(filp); \ int srcu_idx; \ ret_type r; \ \ @@ -176,7 +173,7 @@ static unsigned int full_proxy_poll(struct file *filp, struct poll_table_struct *wait) { const struct dentry *dentry = F_DENTRY(filp); - const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry); + const struct file_operations *real_fops = debugfs_real_fops(filp); int srcu_idx; unsigned int r = 0; @@ -193,7 +190,7 @@ static unsigned int full_proxy_poll(struct file *filp, static int full_proxy_release(struct inode *inode, struct file *filp) { const struct dentry *dentry = F_DENTRY(filp); - const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry); + const struct file_operations *real_fops = debugfs_real_fops(filp); const struct file_operations *proxy_fops = filp->f_op; int r = 0; @@ -209,7 +206,7 @@ static int full_proxy_release(struct inode *inode, struct file *filp) replace_fops(filp, d_inode(dentry)->i_fop); kfree((void *)proxy_fops); fops_put(real_fops); - return 0; + return r; } static void __full_proxy_fops_init(struct file_operations *proxy_fops, @@ -241,7 +238,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) goto out; } - real_fops = REAL_FOPS_DEREF(dentry); + real_fops = debugfs_real_fops(filp); real_fops = fops_get(real_fops); if (!real_fops) { /* Huh? Module did not cleanup after itself at exit? */ diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index bba52634b995..b3e8443a1f47 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -19,8 +19,4 @@ extern const struct file_operations debugfs_noop_file_operations; extern const struct file_operations debugfs_open_proxy_file_operations; extern const struct file_operations debugfs_full_proxy_file_operations; -struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct file_operations *fops); - #endif /* _DEBUGFS_INTERNAL_H_ */ diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 79a5941c2474..442d1a7e671b 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -272,13 +272,8 @@ static int mknod_ptmx(struct super_block *sb) struct dentry *root = sb->s_root; struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; - kuid_t root_uid; - kgid_t root_gid; - - root_uid = make_kuid(current_user_ns(), 0); - root_gid = make_kgid(current_user_ns(), 0); - if (!uid_valid(root_uid) || !gid_valid(root_gid)) - return -EINVAL; + kuid_t ptmx_uid = current_fsuid(); + kgid_t ptmx_gid = current_fsgid(); inode_lock(d_inode(root)); @@ -309,8 +304,8 @@ static int mknod_ptmx(struct super_block *sb) mode = S_IFCHR|opts->ptmxmode; init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2)); - inode->i_uid = root_uid; - inode->i_gid = root_gid; + inode->i_uid = ptmx_uid; + inode->i_gid = ptmx_gid; d_add(dentry, inode); @@ -336,7 +331,6 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data) struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; - sync_filesystem(sb); err = parse_mount_options(data, PARSE_REMOUNT, opts); /* @@ -395,6 +389,7 @@ static int devpts_fill_super(struct super_block *s, void *data, int silent) { struct inode *inode; + int error; s->s_iflags &= ~SB_I_NODEV; s->s_blocksize = 1024; @@ -403,10 +398,16 @@ devpts_fill_super(struct super_block *s, void *data, int silent) s->s_op = &devpts_sops; s->s_time_gran = 1; + error = -ENOMEM; s->s_fs_info = new_pts_fs_info(s); if (!s->s_fs_info) goto fail; + error = parse_mount_options(data, PARSE_MOUNT, &DEVPTS_SB(s)->mount_opts); + if (error) + goto fail; + + error = -ENOMEM; inode = new_inode(s); if (!inode) goto fail; @@ -418,13 +419,21 @@ devpts_fill_super(struct super_block *s, void *data, int silent) set_nlink(inode, 2); s->s_root = d_make_root(inode); - if (s->s_root) - return 0; + if (!s->s_root) { + pr_err("get root dentry failed\n"); + goto fail; + } - pr_err("get root dentry failed\n"); + error = mknod_ptmx(s); + if (error) + goto fail_dput; + return 0; +fail_dput: + dput(s->s_root); + s->s_root = NULL; fail: - return -ENOMEM; + return error; } /* @@ -436,43 +445,15 @@ fail: static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - int error; - struct pts_mount_opts opts; - struct super_block *s; - - error = parse_mount_options(data, PARSE_MOUNT, &opts); - if (error) - return ERR_PTR(error); - - s = sget(fs_type, NULL, set_anon_super, flags, NULL); - if (IS_ERR(s)) - return ERR_CAST(s); - - if (!s->s_root) { - error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0); - if (error) - goto out_undo_sget; - s->s_flags |= MS_ACTIVE; - } - - memcpy(&(DEVPTS_SB(s))->mount_opts, &opts, sizeof(opts)); - - error = mknod_ptmx(s); - if (error) - goto out_undo_sget; - - return dget(s->s_root); - -out_undo_sget: - deactivate_locked_super(s); - return ERR_PTR(error); + return mount_nodev(fs_type, flags, data, devpts_fill_super); } static void devpts_kill_sb(struct super_block *sb) { struct pts_fs_info *fsi = DEVPTS_SB(sb); - ida_destroy(&fsi->allocated_ptys); + if (fsi) + ida_destroy(&fsi->allocated_ptys); kfree(fsi); kill_litter_super(sb); } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 1d73fc6dba13..cbb50cadcffc 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -105,7 +105,10 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, inode->i_private = var; - efivar_entry_add(var, &efivarfs_list); + err = efivar_entry_add(var, &efivarfs_list); + if (err) + goto out; + d_instantiate(dentry, inode); dget(dentry); out: diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 688ccc16b702..d7a7c53803c1 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -157,12 +157,14 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, goto fail_inode; } + efivar_entry_size(entry, &size); + err = efivar_entry_add(entry, &efivarfs_list); + if (err) + goto fail_inode; + /* copied by the above to local storage in the dentry. */ kfree(name); - efivar_entry_size(entry, &size); - efivar_entry_add(entry, &efivarfs_list); - inode_lock(inode); inode->i_private = entry; i_size_write(inode, size + sizeof(entry->var.Attributes)); @@ -182,7 +184,10 @@ fail: static int efivarfs_destroy(struct efivar_entry *entry, void *data) { - efivar_entry_remove(entry); + int err = efivar_entry_remove(entry); + + if (err) + return err; kfree(entry); return 0; } diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index efe5fb21c533..04e73a99902b 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -465,6 +465,11 @@ struct inode *ext2_new_inode(struct inode *dir, umode_t mode, for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext2_get_group_desc(sb, group, &bh2); + if (!gdp) { + if (++group == sbi->s_groups_count) + group = 0; + continue; + } brelse(bitmap_bh); bitmap_bh = read_inode_bitmap(sb, group); if (!bitmap_bh) { diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index d5c7d09919f3..303ae2bb269a 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -733,6 +733,16 @@ static int ext2_get_blocks(struct inode *inode, } if (IS_DAX(inode)) { + int i; + + /* + * We must unmap blocks before zeroing so that writeback cannot + * overwrite zeros with stale data from block device page cache. + */ + for (i = 0; i < count; i++) { + unmap_underlying_metadata(inode->i_sb->s_bdev, + le32_to_cpu(chain[depth-1].key) + i); + } /* * block must be initialised before we put it in the tree * so that it's not found by another thread before it's diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 1b2f6c2c3aaf..76f09ce7e5b2 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -1,5 +1,6 @@ config FUSE_FS tristate "FUSE (Filesystem in Userspace) support" + select FS_POSIX_ACL help With FUSE it is possible to implement a fully functional filesystem in a userspace program. diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index e95eeb445e58..60da84a86dab 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -5,4 +5,4 @@ obj-$(CONFIG_FUSE_FS) += fuse.o obj-$(CONFIG_CUSE) += cuse.o -fuse-objs := dev.o dir.o file.o inode.o control.o +fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c new file mode 100644 index 000000000000..ec85765502f1 --- /dev/null +++ b/fs/fuse/acl.c @@ -0,0 +1,99 @@ +/* + * FUSE: Filesystem in Userspace + * Copyright (C) 2016 Canonical Ltd. <seth.forshee@canonical.com> + * + * This program can be distributed under the terms of the GNU GPL. + * See the file COPYING. + */ + +#include "fuse_i.h" + +#include <linux/posix_acl.h> +#include <linux/posix_acl_xattr.h> + +struct posix_acl *fuse_get_acl(struct inode *inode, int type) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + int size; + const char *name; + void *value = NULL; + struct posix_acl *acl; + + if (!fc->posix_acl || fc->no_getxattr) + return NULL; + + if (type == ACL_TYPE_ACCESS) + name = XATTR_NAME_POSIX_ACL_ACCESS; + else if (type == ACL_TYPE_DEFAULT) + name = XATTR_NAME_POSIX_ACL_DEFAULT; + else + return ERR_PTR(-EOPNOTSUPP); + + value = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!value) + return ERR_PTR(-ENOMEM); + size = fuse_getxattr(inode, name, value, PAGE_SIZE); + if (size > 0) + acl = posix_acl_from_xattr(&init_user_ns, value, size); + else if ((size == 0) || (size == -ENODATA) || + (size == -EOPNOTSUPP && fc->no_getxattr)) + acl = NULL; + else if (size == -ERANGE) + acl = ERR_PTR(-E2BIG); + else + acl = ERR_PTR(size); + + kfree(value); + return acl; +} + +int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + const char *name; + int ret; + + if (!fc->posix_acl || fc->no_setxattr) + return -EOPNOTSUPP; + + if (type == ACL_TYPE_ACCESS) + name = XATTR_NAME_POSIX_ACL_ACCESS; + else if (type == ACL_TYPE_DEFAULT) + name = XATTR_NAME_POSIX_ACL_DEFAULT; + else + return -EINVAL; + + if (acl) { + /* + * Fuse userspace is responsible for updating access + * permissions in the inode, if needed. fuse_setxattr + * invalidates the inode attributes, which will force + * them to be refreshed the next time they are used, + * and it also updates i_ctime. + */ + size_t size = posix_acl_xattr_size(acl->a_count); + void *value; + + if (size > PAGE_SIZE) + return -E2BIG; + + value = kmalloc(size, GFP_KERNEL); + if (!value) + return -ENOMEM; + + ret = posix_acl_to_xattr(&init_user_ns, acl, value, size); + if (ret < 0) { + kfree(value); + return ret; + } + + ret = fuse_setxattr(inode, name, value, size, 0); + kfree(value); + } else { + ret = fuse_removexattr(inode, name); + } + forget_all_cached_acls(inode); + fuse_invalidate_attr(inode); + + return ret; +} diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index a94d2ed81ab4..c41bde26c338 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -767,7 +767,6 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) cs->len = err; cs->offset = off; cs->pg = page; - cs->offset = off; iov_iter_advance(cs->iter, err); } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index c47b7780ce37..f7c84ab835ca 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -13,6 +13,8 @@ #include <linux/sched.h> #include <linux/namei.h> #include <linux/slab.h> +#include <linux/xattr.h> +#include <linux/posix_acl.h> static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx) { @@ -37,47 +39,39 @@ static void fuse_advise_use_readdirplus(struct inode *dir) set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state); } -#if BITS_PER_LONG >= 64 +union fuse_dentry { + u64 time; + struct rcu_head rcu; +}; + static inline void fuse_dentry_settime(struct dentry *entry, u64 time) { - entry->d_time = time; + ((union fuse_dentry *) entry->d_fsdata)->time = time; } static inline u64 fuse_dentry_time(struct dentry *entry) { - return entry->d_time; -} -#else -/* - * On 32 bit archs store the high 32 bits of time in d_fsdata - */ -static void fuse_dentry_settime(struct dentry *entry, u64 time) -{ - entry->d_time = time; - entry->d_fsdata = (void *) (unsigned long) (time >> 32); -} - -static u64 fuse_dentry_time(struct dentry *entry) -{ - return (u64) entry->d_time + - ((u64) (unsigned long) entry->d_fsdata << 32); + return ((union fuse_dentry *) entry->d_fsdata)->time; } -#endif /* * FUSE caches dentries and attributes with separate timeout. The * time in jiffies until the dentry/attributes are valid is stored in - * dentry->d_time and fuse_inode->i_time respectively. + * dentry->d_fsdata and fuse_inode->i_time respectively. */ /* * Calculate the time in jiffies until a dentry/attributes are valid */ -static u64 time_to_jiffies(unsigned long sec, unsigned long nsec) +static u64 time_to_jiffies(u64 sec, u32 nsec) { if (sec || nsec) { - struct timespec ts = {sec, nsec}; - return get_jiffies_64() + timespec_to_jiffies(&ts); + struct timespec64 ts = { + sec, + max_t(u32, nsec, NSEC_PER_SEC - 1) + }; + + return get_jiffies_64() + timespec64_to_jiffies(&ts); } else return 0; } @@ -243,6 +237,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) goto invalid; + forget_all_cached_acls(inode); fuse_change_attributes(inode, &outarg.attr, entry_attr_timeout(&outarg), attr_version); @@ -272,8 +267,23 @@ static int invalid_nodeid(u64 nodeid) return !nodeid || nodeid == FUSE_ROOT_ID; } +static int fuse_dentry_init(struct dentry *dentry) +{ + dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry), GFP_KERNEL); + + return dentry->d_fsdata ? 0 : -ENOMEM; +} +static void fuse_dentry_release(struct dentry *dentry) +{ + union fuse_dentry *fd = dentry->d_fsdata; + + kfree_rcu(fd, rcu); +} + const struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, + .d_init = fuse_dentry_init, + .d_release = fuse_dentry_release, }; int fuse_valid_type(int m) @@ -634,7 +644,7 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry, return create_new_entry(fc, &args, dir, entry, S_IFLNK); } -static inline void fuse_update_ctime(struct inode *inode) +void fuse_update_ctime(struct inode *inode) { if (!IS_NOCMTIME(inode)) { inode->i_ctime = current_fs_time(inode->i_sb); @@ -917,6 +927,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, if (time_before64(fi->i_time, get_jiffies_64())) { r = true; + forget_all_cached_acls(inode); err = fuse_do_getattr(inode, stat, file); } else { r = false; @@ -1017,7 +1028,7 @@ int fuse_allow_current_process(struct fuse_conn *fc) { const struct cred *cred; - if (fc->flags & FUSE_ALLOW_OTHER) + if (fc->allow_other) return 1; cred = current_cred(); @@ -1064,6 +1075,7 @@ static int fuse_perm_getattr(struct inode *inode, int mask) if (mask & MAY_NOT_BLOCK) return -ECHILD; + forget_all_cached_acls(inode); return fuse_do_getattr(inode, NULL, NULL); } @@ -1092,7 +1104,7 @@ static int fuse_permission(struct inode *inode, int mask) /* * If attributes are needed, refresh them before proceeding */ - if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) || + if (fc->default_permissions || ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -1105,7 +1117,7 @@ static int fuse_permission(struct inode *inode, int mask) } } - if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { + if (fc->default_permissions) { err = generic_permission(inode, mask); /* If permission is denied, try to refresh file @@ -1233,6 +1245,7 @@ retry: fi->nlookup++; spin_unlock(&fc->lock); + forget_all_cached_acls(inode); fuse_change_attributes(inode, &o->attr, entry_attr_timeout(o), attr_version); @@ -1605,7 +1618,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, int err; bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode); - if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) + if (!fc->default_permissions) attr->ia_valid |= ATTR_FORCE; err = inode_change_ok(inode, attr); @@ -1702,172 +1715,75 @@ error: static int fuse_setattr(struct dentry *entry, struct iattr *attr) { struct inode *inode = d_inode(entry); - - if (!fuse_allow_current_process(get_fuse_conn(inode))) - return -EACCES; - - if (attr->ia_valid & ATTR_FILE) - return fuse_do_setattr(inode, attr, attr->ia_file); - else - return fuse_do_setattr(inode, attr, NULL); -} - -static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, - struct kstat *stat) -{ - struct inode *inode = d_inode(entry); struct fuse_conn *fc = get_fuse_conn(inode); + struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL; + int ret; - if (!fuse_allow_current_process(fc)) + if (!fuse_allow_current_process(get_fuse_conn(inode))) return -EACCES; - return fuse_update_attributes(inode, stat, NULL, NULL); -} - -static int fuse_setxattr(struct dentry *unused, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) -{ - struct fuse_conn *fc = get_fuse_conn(inode); - FUSE_ARGS(args); - struct fuse_setxattr_in inarg; - int err; - - if (fc->no_setxattr) - return -EOPNOTSUPP; + if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) { + attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | + ATTR_MODE); - memset(&inarg, 0, sizeof(inarg)); - inarg.size = size; - inarg.flags = flags; - args.in.h.opcode = FUSE_SETXATTR; - args.in.h.nodeid = get_node_id(inode); - args.in.numargs = 3; - args.in.args[0].size = sizeof(inarg); - args.in.args[0].value = &inarg; - args.in.args[1].size = strlen(name) + 1; - args.in.args[1].value = name; - args.in.args[2].size = size; - args.in.args[2].value = value; - err = fuse_simple_request(fc, &args); - if (err == -ENOSYS) { - fc->no_setxattr = 1; - err = -EOPNOTSUPP; - } - if (!err) { - fuse_invalidate_attr(inode); - fuse_update_ctime(inode); + /* + * The only sane way to reliably kill suid/sgid is to do it in + * the userspace filesystem + * + * This should be done on write(), truncate() and chown(). + */ + if (!fc->handle_killpriv) { + int kill; + + /* + * ia_mode calculation may have used stale i_mode. + * Refresh and recalculate. + */ + ret = fuse_do_getattr(inode, NULL, file); + if (ret) + return ret; + + attr->ia_mode = inode->i_mode; + kill = should_remove_suid(entry); + if (kill & ATTR_KILL_SUID) { + attr->ia_valid |= ATTR_MODE; + attr->ia_mode &= ~S_ISUID; + } + if (kill & ATTR_KILL_SGID) { + attr->ia_valid |= ATTR_MODE; + attr->ia_mode &= ~S_ISGID; + } + } } - return err; -} - -static ssize_t fuse_getxattr(struct dentry *entry, struct inode *inode, - const char *name, void *value, size_t size) -{ - struct fuse_conn *fc = get_fuse_conn(inode); - FUSE_ARGS(args); - struct fuse_getxattr_in inarg; - struct fuse_getxattr_out outarg; - ssize_t ret; + if (!attr->ia_valid) + return 0; - if (fc->no_getxattr) - return -EOPNOTSUPP; + ret = fuse_do_setattr(inode, attr, file); + if (!ret) { + /* + * If filesystem supports acls it may have updated acl xattrs in + * the filesystem, so forget cached acls for the inode. + */ + if (fc->posix_acl) + forget_all_cached_acls(inode); - memset(&inarg, 0, sizeof(inarg)); - inarg.size = size; - args.in.h.opcode = FUSE_GETXATTR; - args.in.h.nodeid = get_node_id(inode); - args.in.numargs = 2; - args.in.args[0].size = sizeof(inarg); - args.in.args[0].value = &inarg; - args.in.args[1].size = strlen(name) + 1; - args.in.args[1].value = name; - /* This is really two different operations rolled into one */ - args.out.numargs = 1; - if (size) { - args.out.argvar = 1; - args.out.args[0].size = size; - args.out.args[0].value = value; - } else { - args.out.args[0].size = sizeof(outarg); - args.out.args[0].value = &outarg; - } - ret = fuse_simple_request(fc, &args); - if (!ret && !size) - ret = outarg.size; - if (ret == -ENOSYS) { - fc->no_getxattr = 1; - ret = -EOPNOTSUPP; + /* Directory mode changed, may need to revalidate access */ + if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE)) + fuse_invalidate_entry_cache(entry); } return ret; } -static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) +static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, + struct kstat *stat) { struct inode *inode = d_inode(entry); struct fuse_conn *fc = get_fuse_conn(inode); - FUSE_ARGS(args); - struct fuse_getxattr_in inarg; - struct fuse_getxattr_out outarg; - ssize_t ret; if (!fuse_allow_current_process(fc)) return -EACCES; - if (fc->no_listxattr) - return -EOPNOTSUPP; - - memset(&inarg, 0, sizeof(inarg)); - inarg.size = size; - args.in.h.opcode = FUSE_LISTXATTR; - args.in.h.nodeid = get_node_id(inode); - args.in.numargs = 1; - args.in.args[0].size = sizeof(inarg); - args.in.args[0].value = &inarg; - /* This is really two different operations rolled into one */ - args.out.numargs = 1; - if (size) { - args.out.argvar = 1; - args.out.args[0].size = size; - args.out.args[0].value = list; - } else { - args.out.args[0].size = sizeof(outarg); - args.out.args[0].value = &outarg; - } - ret = fuse_simple_request(fc, &args); - if (!ret && !size) - ret = outarg.size; - if (ret == -ENOSYS) { - fc->no_listxattr = 1; - ret = -EOPNOTSUPP; - } - return ret; -} - -static int fuse_removexattr(struct dentry *entry, const char *name) -{ - struct inode *inode = d_inode(entry); - struct fuse_conn *fc = get_fuse_conn(inode); - FUSE_ARGS(args); - int err; - - if (fc->no_removexattr) - return -EOPNOTSUPP; - - args.in.h.opcode = FUSE_REMOVEXATTR; - args.in.h.nodeid = get_node_id(inode); - args.in.numargs = 1; - args.in.args[0].size = strlen(name) + 1; - args.in.args[0].value = name; - err = fuse_simple_request(fc, &args); - if (err == -ENOSYS) { - fc->no_removexattr = 1; - err = -EOPNOTSUPP; - } - if (!err) { - fuse_invalidate_attr(inode); - fuse_update_ctime(inode); - } - return err; + return fuse_update_attributes(inode, stat, NULL, NULL); } static const struct inode_operations fuse_dir_inode_operations = { @@ -1884,10 +1800,12 @@ static const struct inode_operations fuse_dir_inode_operations = { .mknod = fuse_mknod, .permission = fuse_permission, .getattr = fuse_getattr, - .setxattr = fuse_setxattr, - .getxattr = fuse_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = fuse_listxattr, - .removexattr = fuse_removexattr, + .removexattr = generic_removexattr, + .get_acl = fuse_get_acl, + .set_acl = fuse_set_acl, }; static const struct file_operations fuse_dir_operations = { @@ -1905,10 +1823,12 @@ static const struct inode_operations fuse_common_inode_operations = { .setattr = fuse_setattr, .permission = fuse_permission, .getattr = fuse_getattr, - .setxattr = fuse_setxattr, - .getxattr = fuse_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = fuse_listxattr, - .removexattr = fuse_removexattr, + .removexattr = generic_removexattr, + .get_acl = fuse_get_acl, + .set_acl = fuse_set_acl, }; static const struct inode_operations fuse_symlink_inode_operations = { @@ -1916,10 +1836,10 @@ static const struct inode_operations fuse_symlink_inode_operations = { .get_link = fuse_get_link, .readlink = generic_readlink, .getattr = fuse_getattr, - .setxattr = fuse_setxattr, - .getxattr = fuse_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = fuse_listxattr, - .removexattr = fuse_removexattr, + .removexattr = generic_removexattr, }; void fuse_init_common(struct inode *inode) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 3988b43c2f5a..b7beb67bf005 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2326,49 +2326,6 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence) return retval; } -static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov, - unsigned int nr_segs, size_t bytes, bool to_user) -{ - struct iov_iter ii; - int page_idx = 0; - - if (!bytes) - return 0; - - iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes); - - while (iov_iter_count(&ii)) { - struct page *page = pages[page_idx++]; - size_t todo = min_t(size_t, PAGE_SIZE, iov_iter_count(&ii)); - void *kaddr; - - kaddr = kmap(page); - - while (todo) { - char __user *uaddr = ii.iov->iov_base + ii.iov_offset; - size_t iov_len = ii.iov->iov_len - ii.iov_offset; - size_t copy = min(todo, iov_len); - size_t left; - - if (!to_user) - left = copy_from_user(kaddr, uaddr, copy); - else - left = copy_to_user(uaddr, kaddr, copy); - - if (unlikely(left)) - return -EFAULT; - - iov_iter_advance(&ii, copy); - todo -= copy; - kaddr += copy; - } - - kunmap(page); - } - - return 0; -} - /* * CUSE servers compiled on 32bit broke on 64bit kernels because the * ABI was defined to be 'struct iovec' which is different on 32bit @@ -2520,8 +2477,9 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, struct iovec *iov_page = NULL; struct iovec *in_iov = NULL, *out_iov = NULL; unsigned int in_iovs = 0, out_iovs = 0, num_pages = 0, max_pages; - size_t in_size, out_size, transferred; - int err; + size_t in_size, out_size, transferred, c; + int err, i; + struct iov_iter ii; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; @@ -2603,10 +2561,13 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, req->in.args[1].size = in_size; req->in.argpages = 1; - err = fuse_ioctl_copy_user(pages, in_iov, in_iovs, in_size, - false); - if (err) - goto out; + err = -EFAULT; + iov_iter_init(&ii, WRITE, in_iov, in_iovs, in_size); + for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= num_pages); i++) { + c = copy_page_from_iter(pages[i], 0, PAGE_SIZE, &ii); + if (c != PAGE_SIZE && iov_iter_count(&ii)) + goto out; + } } req->out.numargs = 2; @@ -2672,7 +2633,14 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, if (transferred > inarg.out_size) goto out; - err = fuse_ioctl_copy_user(pages, out_iov, out_iovs, transferred, true); + err = -EFAULT; + iov_iter_init(&ii, READ, out_iov, out_iovs, transferred); + for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= num_pages); i++) { + c = copy_page_to_iter(pages[i], 0, PAGE_SIZE, &ii); + if (c != PAGE_SIZE && iov_iter_count(&ii)) + goto out; + } + err = 0; out: if (req) fuse_put_request(fc, req); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index d98d8cc84def..24ada5dc4dae 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -23,6 +23,7 @@ #include <linux/poll.h> #include <linux/workqueue.h> #include <linux/kref.h> +#include <linux/xattr.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32 @@ -36,15 +37,6 @@ /** Number of dentries for each connection in the control filesystem */ #define FUSE_CTL_NUM_DENTRIES 5 -/** If the FUSE_DEFAULT_PERMISSIONS flag is given, the filesystem - module will check permissions based on the file mode. Otherwise no - permission checking is done in the kernel */ -#define FUSE_DEFAULT_PERMISSIONS (1 << 0) - -/** If the FUSE_ALLOW_OTHER flag is given, then not only the user - doing the mount will be allowed to access the filesystem */ -#define FUSE_ALLOW_OTHER (1 << 1) - /** Number of page pointers embedded in fuse_req */ #define FUSE_REQ_INLINE_PAGES 1 @@ -469,9 +461,6 @@ struct fuse_conn { /** The group id for this mount */ kgid_t group_id; - /** The fuse mount flags for this mount */ - unsigned flags; - /** Maximum read size */ unsigned max_read; @@ -547,6 +536,9 @@ struct fuse_conn { /** allow parallel lookups and readdir (default is serialized) */ unsigned parallel_dirops:1; + /** handle fs handles killing suid/sgid/cap on write/chown/trunc */ + unsigned handle_killpriv:1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction @@ -624,6 +616,15 @@ struct fuse_conn { /** Is lseek not implemented by fs? */ unsigned no_lseek:1; + /** Does the filesystem support posix acls? */ + unsigned posix_acl:1; + + /** Check permissions based on the file mode or not? */ + unsigned default_permissions:1; + + /** Allow other than the mounter user to access the filesystem ? */ + unsigned allow_other:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; @@ -902,6 +903,8 @@ int fuse_allow_current_process(struct fuse_conn *fc); u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id); +void fuse_update_ctime(struct inode *inode); + int fuse_update_attributes(struct inode *inode, struct kstat *stat, struct file *file, bool *refreshed); @@ -966,4 +969,17 @@ void fuse_set_initialized(struct fuse_conn *fc); void fuse_unlock_inode(struct inode *inode); void fuse_lock_inode(struct inode *inode); +int fuse_setxattr(struct inode *inode, const char *name, const void *value, + size_t size, int flags); +ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, + size_t size); +ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size); +int fuse_removexattr(struct inode *inode, const char *name); +extern const struct xattr_handler *fuse_xattr_handlers[]; +extern const struct xattr_handler *fuse_acl_xattr_handlers[]; + +struct posix_acl; +struct posix_acl *fuse_get_acl(struct inode *inode, int type); +int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type); + #endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 4e05b51120f4..17141099f2e7 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -20,6 +20,7 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/exportfs.h> +#include <linux/posix_acl.h> MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); MODULE_DESCRIPTION("Filesystem in Userspace"); @@ -66,7 +67,8 @@ struct fuse_mount_data { unsigned rootmode_present:1; unsigned user_id_present:1; unsigned group_id_present:1; - unsigned flags; + unsigned default_permissions:1; + unsigned allow_other:1; unsigned max_read; unsigned blksize; }; @@ -192,7 +194,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, * check in may_delete(). */ fi->orig_i_mode = inode->i_mode; - if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) + if (!fc->default_permissions) inode->i_mode &= ~S_ISVTX; fi->orig_ino = attr->ino; @@ -340,6 +342,7 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, return -ENOENT; fuse_invalidate_attr(inode); + forget_all_cached_acls(inode); if (offset >= 0) { pg_start = offset >> PAGE_SHIFT; if (len <= 0) @@ -532,11 +535,11 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) break; case OPT_DEFAULT_PERMISSIONS: - d->flags |= FUSE_DEFAULT_PERMISSIONS; + d->default_permissions = 1; break; case OPT_ALLOW_OTHER: - d->flags |= FUSE_ALLOW_OTHER; + d->allow_other = 1; break; case OPT_MAX_READ: @@ -570,9 +573,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",user_id=%u", from_kuid_munged(&init_user_ns, fc->user_id)); seq_printf(m, ",group_id=%u", from_kgid_munged(&init_user_ns, fc->group_id)); - if (fc->flags & FUSE_DEFAULT_PERMISSIONS) + if (fc->default_permissions) seq_puts(m, ",default_permissions"); - if (fc->flags & FUSE_ALLOW_OTHER) + if (fc->allow_other) seq_puts(m, ",allow_other"); if (fc->max_read != ~0) seq_printf(m, ",max_read=%u", fc->max_read); @@ -910,8 +913,15 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->writeback_cache = 1; if (arg->flags & FUSE_PARALLEL_DIROPS) fc->parallel_dirops = 1; + if (arg->flags & FUSE_HANDLE_KILLPRIV) + fc->handle_killpriv = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fc->sb->s_time_gran = arg->time_gran; + if ((arg->flags & FUSE_POSIX_ACL)) { + fc->default_permissions = 1; + fc->posix_acl = 1; + fc->sb->s_xattr = fuse_acl_xattr_handlers; + } } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -941,7 +951,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | - FUSE_PARALLEL_DIROPS; + FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); @@ -1071,6 +1081,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) } sb->s_magic = FUSE_SUPER_MAGIC; sb->s_op = &fuse_super_operations; + sb->s_xattr = fuse_xattr_handlers; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_gran = 1; sb->s_export_op = &fuse_export_operations; @@ -1109,7 +1120,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->dont_mask = 1; sb->s_flags |= MS_POSIXACL; - fc->flags = d.flags; + fc->default_permissions = d.default_permissions; + fc->allow_other = d.allow_other; fc->user_id = d.user_id; fc->group_id = d.group_id; fc->max_read = max_t(unsigned, 4096, d.max_read); diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c new file mode 100644 index 000000000000..3caac46b08b0 --- /dev/null +++ b/fs/fuse/xattr.c @@ -0,0 +1,211 @@ +/* + * FUSE: Filesystem in Userspace + * Copyright (C) 2001-2016 Miklos Szeredi <miklos@szeredi.hu> + * + * This program can be distributed under the terms of the GNU GPL. + * See the file COPYING. + */ + +#include "fuse_i.h" + +#include <linux/xattr.h> +#include <linux/posix_acl_xattr.h> + +int fuse_setxattr(struct inode *inode, const char *name, const void *value, + size_t size, int flags) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + FUSE_ARGS(args); + struct fuse_setxattr_in inarg; + int err; + + if (fc->no_setxattr) + return -EOPNOTSUPP; + + memset(&inarg, 0, sizeof(inarg)); + inarg.size = size; + inarg.flags = flags; + args.in.h.opcode = FUSE_SETXATTR; + args.in.h.nodeid = get_node_id(inode); + args.in.numargs = 3; + args.in.args[0].size = sizeof(inarg); + args.in.args[0].value = &inarg; + args.in.args[1].size = strlen(name) + 1; + args.in.args[1].value = name; + args.in.args[2].size = size; + args.in.args[2].value = value; + err = fuse_simple_request(fc, &args); + if (err == -ENOSYS) { + fc->no_setxattr = 1; + err = -EOPNOTSUPP; + } + if (!err) { + fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } + return err; +} + +ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, + size_t size) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + FUSE_ARGS(args); + struct fuse_getxattr_in inarg; + struct fuse_getxattr_out outarg; + ssize_t ret; + + if (fc->no_getxattr) + return -EOPNOTSUPP; + + memset(&inarg, 0, sizeof(inarg)); + inarg.size = size; + args.in.h.opcode = FUSE_GETXATTR; + args.in.h.nodeid = get_node_id(inode); + args.in.numargs = 2; + args.in.args[0].size = sizeof(inarg); + args.in.args[0].value = &inarg; + args.in.args[1].size = strlen(name) + 1; + args.in.args[1].value = name; + /* This is really two different operations rolled into one */ + args.out.numargs = 1; + if (size) { + args.out.argvar = 1; + args.out.args[0].size = size; + args.out.args[0].value = value; + } else { + args.out.args[0].size = sizeof(outarg); + args.out.args[0].value = &outarg; + } + ret = fuse_simple_request(fc, &args); + if (!ret && !size) + ret = min_t(ssize_t, outarg.size, XATTR_SIZE_MAX); + if (ret == -ENOSYS) { + fc->no_getxattr = 1; + ret = -EOPNOTSUPP; + } + return ret; +} + +static int fuse_verify_xattr_list(char *list, size_t size) +{ + size_t origsize = size; + + while (size) { + size_t thislen = strnlen(list, size); + + if (!thislen || thislen == size) + return -EIO; + + size -= thislen + 1; + list += thislen + 1; + } + + return origsize; +} + +ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) +{ + struct inode *inode = d_inode(entry); + struct fuse_conn *fc = get_fuse_conn(inode); + FUSE_ARGS(args); + struct fuse_getxattr_in inarg; + struct fuse_getxattr_out outarg; + ssize_t ret; + + if (!fuse_allow_current_process(fc)) + return -EACCES; + + if (fc->no_listxattr) + return -EOPNOTSUPP; + + memset(&inarg, 0, sizeof(inarg)); + inarg.size = size; + args.in.h.opcode = FUSE_LISTXATTR; + args.in.h.nodeid = get_node_id(inode); + args.in.numargs = 1; + args.in.args[0].size = sizeof(inarg); + args.in.args[0].value = &inarg; + /* This is really two different operations rolled into one */ + args.out.numargs = 1; + if (size) { + args.out.argvar = 1; + args.out.args[0].size = size; + args.out.args[0].value = list; + } else { + args.out.args[0].size = sizeof(outarg); + args.out.args[0].value = &outarg; + } + ret = fuse_simple_request(fc, &args); + if (!ret && !size) + ret = min_t(ssize_t, outarg.size, XATTR_LIST_MAX); + if (ret > 0 && size) + ret = fuse_verify_xattr_list(list, ret); + if (ret == -ENOSYS) { + fc->no_listxattr = 1; + ret = -EOPNOTSUPP; + } + return ret; +} + +int fuse_removexattr(struct inode *inode, const char *name) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + FUSE_ARGS(args); + int err; + + if (fc->no_removexattr) + return -EOPNOTSUPP; + + args.in.h.opcode = FUSE_REMOVEXATTR; + args.in.h.nodeid = get_node_id(inode); + args.in.numargs = 1; + args.in.args[0].size = strlen(name) + 1; + args.in.args[0].value = name; + err = fuse_simple_request(fc, &args); + if (err == -ENOSYS) { + fc->no_removexattr = 1; + err = -EOPNOTSUPP; + } + if (!err) { + fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } + return err; +} + +static int fuse_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) +{ + return fuse_getxattr(inode, name, value, size); +} + +static int fuse_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, size_t size, + int flags) +{ + if (!value) + return fuse_removexattr(inode, name); + + return fuse_setxattr(inode, name, value, size, flags); +} + +static const struct xattr_handler fuse_xattr_handler = { + .prefix = "", + .get = fuse_xattr_get, + .set = fuse_xattr_set, +}; + +const struct xattr_handler *fuse_xattr_handlers[] = { + &fuse_xattr_handler, + NULL +}; + +const struct xattr_handler *fuse_acl_xattr_handlers[] = { + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, + &fuse_xattr_handler, + NULL +}; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 82df36886938..5a6f52ea2722 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -187,7 +187,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w ClearPageChecked(page); if (!page_has_buffers(page)) { create_empty_buffers(page, inode->i_sb->s_blocksize, - (1 << BH_Dirty)|(1 << BH_Uptodate)); + BIT(BH_Dirty)|BIT(BH_Uptodate)); } gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1); } @@ -1147,6 +1147,16 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) if (!page_has_buffers(page)) return 0; + /* + * From xfs_vm_releasepage: mm accommodates an old ext3 case where + * clean pages might not have had the dirty bit cleared. Thus, it can + * send actual dirty pages to ->releasepage() via shrink_active_list(). + * + * As a workaround, we skip pages that contain dirty buffers below. + * Once ->releasepage isn't called on dirty pages anymore, we can warn + * on dirty buffers like we used to here again. + */ + gfs2_log_lock(sdp); spin_lock(&sdp->sd_ail_lock); head = bh = page_buffers(page); @@ -1156,8 +1166,8 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) bd = bh->b_private; if (bd && bd->bd_tr) goto cannot_release; - if (buffer_pinned(bh) || buffer_dirty(bh)) - goto not_possible; + if (buffer_dirty(bh) || WARN_ON(buffer_pinned(bh))) + goto cannot_release; bh = bh->b_this_page; } while(bh != head); spin_unlock(&sdp->sd_ail_lock); @@ -1180,9 +1190,6 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) return try_to_free_buffers(page); -not_possible: /* Should never happen */ - WARN_ON(buffer_dirty(bh)); - WARN_ON(buffer_pinned(bh)); cannot_release: spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 6e2bec1cd289..645721f3ff00 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -82,8 +82,8 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, } if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << inode->i_blkbits, - (1 << BH_Uptodate)); + create_empty_buffers(page, BIT(inode->i_blkbits), + BIT(BH_Uptodate)); bh = page_buffers(page); @@ -690,7 +690,7 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi BUG_ON(!dblock); BUG_ON(!new); - bh.b_size = 1 << (inode->i_blkbits + (create ? 0 : 5)); + bh.b_size = BIT(inode->i_blkbits + (create ? 0 : 5)); ret = gfs2_block_map(inode, lblock, &bh, create); *extlen = bh.b_size >> inode->i_blkbits; *dblock = bh.b_blocknr; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index fcb59b23f1e3..db8fbeb62483 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -351,7 +351,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) if (hc) return hc; - hsize = 1 << ip->i_depth; + hsize = BIT(ip->i_depth); hsize *= sizeof(__be64); if (hsize != i_size_read(&ip->i_inode)) { gfs2_consist_inode(ip); @@ -819,8 +819,8 @@ static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode, if (ip->i_diskflags & GFS2_DIF_EXHASH) { struct gfs2_leaf *leaf; - unsigned hsize = 1 << ip->i_depth; - unsigned index; + unsigned int hsize = BIT(ip->i_depth); + unsigned int index; u64 ln; if (hsize * sizeof(u64) != i_size_read(inode)) { gfs2_consist_inode(ip); @@ -932,7 +932,7 @@ static int dir_make_exhash(struct inode *inode) return -ENOSPC; bn = bh->b_blocknr; - gfs2_assert(sdp, dip->i_entries < (1 << 16)); + gfs2_assert(sdp, dip->i_entries < BIT(16)); leaf->lf_entries = cpu_to_be16(dip->i_entries); /* Copy dirents */ @@ -1041,7 +1041,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) bn = nbh->b_blocknr; /* Compute the start and len of leaf pointers in the hash table. */ - len = 1 << (dip->i_depth - be16_to_cpu(oleaf->lf_depth)); + len = BIT(dip->i_depth - be16_to_cpu(oleaf->lf_depth)); half_len = len >> 1; if (!half_len) { pr_warn("i_depth %u lf_depth %u index %u\n", @@ -1163,7 +1163,7 @@ static int dir_double_exhash(struct gfs2_inode *dip) int x; int error = 0; - hsize = 1 << dip->i_depth; + hsize = BIT(dip->i_depth); hsize_bytes = hsize * sizeof(__be64); hc = gfs2_dir_get_hash_table(dip); @@ -1539,7 +1539,7 @@ static int dir_e_read(struct inode *inode, struct dir_context *ctx, int error = 0; unsigned depth = 0; - hsize = 1 << dip->i_depth; + hsize = BIT(dip->i_depth); hash = gfs2_dir_offset2hash(ctx->pos); index = hash >> (32 - dip->i_depth); @@ -1558,7 +1558,7 @@ static int dir_e_read(struct inode *inode, struct dir_context *ctx, if (error) break; - len = 1 << (dip->i_depth - depth); + len = BIT(dip->i_depth - depth); index = (index & ~(len - 1)) + len; } @@ -2113,7 +2113,7 @@ int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip) u64 leaf_no; int error = 0, last; - hsize = 1 << dip->i_depth; + hsize = BIT(dip->i_depth); lp = gfs2_dir_get_hash_table(dip); if (IS_ERR(lp)) @@ -2126,7 +2126,7 @@ int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip) if (error) goto out; leaf = (struct gfs2_leaf *)bh->b_data; - len = 1 << (dip->i_depth - be16_to_cpu(leaf->lf_depth)); + len = BIT(dip->i_depth - be16_to_cpu(leaf->lf_depth)); next_index = (index & ~(len - 1)) + len; last = ((next_index >= hsize) ? 1 : 0); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 320e65e61938..360188f162bd 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -395,9 +395,6 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); - /* Update file times before taking page lock */ - file_update_time(vma->vm_file); - ret = gfs2_rsqa_alloc(ip); if (ret) goto out; @@ -409,6 +406,9 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto out_uninit; + /* Update file times before taking page lock */ + file_update_time(vma->vm_file); + set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); set_bit(GIF_SW_PAGED, &ip->i_flags); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 3a90b2b5b9bb..14cbf60167a7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -69,7 +69,7 @@ static atomic_t lru_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(lru_lock); #define GFS2_GL_HASH_SHIFT 15 -#define GFS2_GL_HASH_SIZE (1 << GFS2_GL_HASH_SHIFT) +#define GFS2_GL_HASH_SIZE BIT(GFS2_GL_HASH_SHIFT) static struct rhashtable_params ht_parms = { .nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4, @@ -1781,7 +1781,13 @@ int __init gfs2_glock_init(void) return -ENOMEM; } - register_shrinker(&glock_shrinker); + ret = register_shrinker(&glock_shrinker); + if (ret) { + destroy_workqueue(gfs2_delete_workqueue); + destroy_workqueue(glock_workqueue); + rhashtable_destroy(&gl_hash_table); + return ret; + } return 0; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index e4da0ecd3285..fb3a810b506f 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -187,6 +187,10 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, } gfs2_set_iop(inode); + + inode->i_atime.tv_sec = 0; + inode->i_atime.tv_nsec = 0; + unlock_new_inode(inode); } diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 7710dfd3af35..aace8ce34a18 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -85,7 +85,7 @@ static inline int gfs2_check_internal_file_size(struct inode *inode, u64 size = i_size_read(inode); if (size < minsize || size > maxsize) goto err; - if (size & ((1 << inode->i_blkbits) - 1)) + if (size & (BIT(inode->i_blkbits) - 1)) goto err; return 0; err: diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 74fd0139e6c2..67d1fc4668f7 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -145,7 +145,9 @@ static int __init init_gfs2_fs(void) if (!gfs2_qadata_cachep) goto fail; - register_shrinker(&gfs2_qd_shrinker); + error = register_shrinker(&gfs2_qd_shrinker); + if (error) + goto fail; error = register_filesystem(&gfs2_fs_type); if (error) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 950b8be68e41..373639a59782 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -216,23 +216,26 @@ static void gfs2_meta_read_endio(struct bio *bio) static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[], int num) { - struct buffer_head *bh = bhs[0]; - struct bio *bio; - int i; - - if (!num) - return; - - bio = bio_alloc(GFP_NOIO, num); - bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_bdev = bh->b_bdev; - for (i = 0; i < num; i++) { - bh = bhs[i]; - bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); + while (num > 0) { + struct buffer_head *bh = *bhs; + struct bio *bio; + + bio = bio_alloc(GFP_NOIO, num); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); + bio->bi_bdev = bh->b_bdev; + while (num > 0) { + bh = *bhs; + if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) { + BUG_ON(bio->bi_iter.bi_size == 0); + break; + } + bhs++; + num--; + } + bio->bi_end_io = gfs2_meta_read_endio; + bio_set_op_attrs(bio, op, op_flags); + submit_bio(bio); } - bio->bi_end_io = gfs2_meta_read_endio; - bio_set_op_attrs(bio, op, op_flags); - submit_bio(bio); } /** diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index ef1e1822977f..ff72ac6439c8 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -58,7 +58,7 @@ static void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_quota_scale_num = 1; gt->gt_quota_scale_den = 1; gt->gt_new_files_jdata = 0; - gt->gt_max_readahead = 1 << 18; + gt->gt_max_readahead = BIT(18); gt->gt_complain_secs = 10; } @@ -284,7 +284,7 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent) sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT; - sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift; + sdp->sd_fsb2bb = BIT(sdp->sd_fsb2bb_shift); sdp->sd_diptrs = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) / sizeof(u64); sdp->sd_inptrs = (sdp->sd_sb.sb_bsize - @@ -302,7 +302,7 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent) /* Compute maximum reservation required to add a entry to a directory */ - hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH), + hash_blocks = DIV_ROUND_UP(sizeof(u64) * BIT(GFS2_DIR_MAX_DEPTH), sdp->sd_jbsize); ind_blocks = 0; @@ -1089,7 +1089,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent sdp->sd_sb.sb_bsize_shift = sb->s_blocksize_bits; sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT; - sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift; + sdp->sd_fsb2bb = BIT(sdp->sd_fsb2bb_shift); sdp->sd_tune.gt_logd_secs = sdp->sd_args.ar_commit; sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 77930ca25303..8af2dfa09236 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -75,7 +75,7 @@ #include "util.h" #define GFS2_QD_HASH_SHIFT 12 -#define GFS2_QD_HASH_SIZE (1 << GFS2_QD_HASH_SHIFT) +#define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT) #define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1) /* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */ @@ -384,7 +384,7 @@ static int bh_get(struct gfs2_quota_data *qd) block = qd->qd_slot / sdp->sd_qc_per_block; offset = qd->qd_slot % sdp->sd_qc_per_block; - bh_map.b_size = 1 << ip->i_inode.i_blkbits; + bh_map.b_size = BIT(ip->i_inode.i_blkbits); error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0); if (error) goto fail; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 3a7e60bb39f8..e3ee387a6dfe 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -359,7 +359,7 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd) struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); u64 size = i_size_read(jd->jd_inode); - if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, 1 << 30)) + if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, BIT(30))) return -EIO; jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift; diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 2e58978d6f45..4d973524c887 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -2893,8 +2893,7 @@ restart: * on anon_list2. Let's check. */ if (!list_empty(&TxAnchor.anon_list2)) { - list_splice(&TxAnchor.anon_list2, &TxAnchor.anon_list); - INIT_LIST_HEAD(&TxAnchor.anon_list2); + list_splice_init(&TxAnchor.anon_list2, &TxAnchor.anon_list); goto restart; } TXN_UNLOCK(); diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 90b3bc21e9b0..bd9b641ada2c 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -379,8 +379,14 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) * cached in meta-data cache, and not written out * by txCommit(); */ - filemap_fdatawait(ipbmap->i_mapping); - filemap_write_and_wait(ipbmap->i_mapping); + rc = filemap_fdatawait(ipbmap->i_mapping); + if (rc) + goto error_out; + + rc = filemap_write_and_wait(ipbmap->i_mapping); + if (rc) + goto error_out; + diWriteSpecial(ipbmap, 0); newPage = nPages; /* first new page number */ diff --git a/fs/locks.c b/fs/locks.c index ee1b15f6fc13..90ec67108b22 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -127,7 +127,6 @@ #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> -#include <linux/lglock.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> @@ -158,12 +157,18 @@ int lease_break_time = 45; /* * The global file_lock_list is only used for displaying /proc/locks, so we - * keep a list on each CPU, with each list protected by its own spinlock via - * the file_lock_lglock. Note that alterations to the list also require that - * the relevant flc_lock is held. + * keep a list on each CPU, with each list protected by its own spinlock. + * Global serialization is done using file_rwsem. + * + * Note that alterations to the list also require that the relevant flc_lock is + * held. */ -DEFINE_STATIC_LGLOCK(file_lock_lglock); -static DEFINE_PER_CPU(struct hlist_head, file_lock_list); +struct file_lock_list_struct { + spinlock_t lock; + struct hlist_head hlist; +}; +static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); +DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. @@ -587,15 +592,23 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) /* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { - lg_local_lock(&file_lock_lglock); + struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); + + percpu_rwsem_assert_held(&file_rwsem); + + spin_lock(&fll->lock); fl->fl_link_cpu = smp_processor_id(); - hlist_add_head(&fl->fl_link, this_cpu_ptr(&file_lock_list)); - lg_local_unlock(&file_lock_lglock); + hlist_add_head(&fl->fl_link, &fll->hlist); + spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { + struct file_lock_list_struct *fll; + + percpu_rwsem_assert_held(&file_rwsem); + /* * Avoid taking lock if already unhashed. This is safe since this check * is done while holding the flc_lock, and new insertions into the list @@ -603,9 +616,11 @@ static void locks_delete_global_locks(struct file_lock *fl) */ if (hlist_unhashed(&fl->fl_link)) return; - lg_local_lock_cpu(&file_lock_lglock, fl->fl_link_cpu); + + fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu); + spin_lock(&fll->lock); hlist_del_init(&fl->fl_link); - lg_local_unlock_cpu(&file_lock_lglock, fl->fl_link_cpu); + spin_unlock(&fll->lock); } static unsigned long @@ -915,6 +930,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) return -ENOMEM; } + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -955,6 +971,7 @@ find_conflict: out: spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -991,6 +1008,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, new_fl2 = locks_alloc_lock(); } + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If @@ -1162,6 +1180,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, } out: spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); /* * Free any unused locks. */ @@ -1436,6 +1455,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1487,9 +1507,13 @@ restart: locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); + locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); + + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); @@ -1506,6 +1530,7 @@ restart: } out: spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1660,6 +1685,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg, lease->fl_flags); @@ -1730,6 +1756,7 @@ out_setup: lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); @@ -1752,6 +1779,7 @@ static int generic_delete_lease(struct file *filp, void *owner) return error; } + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && @@ -1764,6 +1792,7 @@ static int generic_delete_lease(struct file *filp, void *owner) if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); locks_dispose_list(&dispose); return error; } @@ -2574,9 +2603,20 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, struct inode *inode = NULL; unsigned int fl_pid; - if (fl->fl_nspid) - fl_pid = pid_vnr(fl->fl_nspid); - else + if (fl->fl_nspid) { + struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; + + /* Don't let fl_pid change based on who is reading the file */ + fl_pid = pid_nr_ns(fl->fl_nspid, proc_pidns); + + /* + * If there isn't a fl_pid don't display who is waiting on + * the lock if we are called from locks_show, or if we are + * called from __show_fd_info - skip lock entirely + */ + if (fl_pid == 0) + return; + } else fl_pid = fl->fl_pid; if (fl->fl_file != NULL) @@ -2648,9 +2688,13 @@ static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock *fl, *bfl; + struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; fl = hlist_entry(v, struct file_lock, fl_link); + if (fl->fl_nspid && !pid_nr_ns(fl->fl_nspid, proc_pidns)) + return 0; + lock_get_status(f, fl, iter->li_pos, ""); list_for_each_entry(bfl, &fl->fl_block, fl_block) @@ -2703,9 +2747,9 @@ static void *locks_start(struct seq_file *f, loff_t *pos) struct locks_iterator *iter = f->private; iter->li_pos = *pos + 1; - lg_global_lock(&file_lock_lglock); + percpu_down_write(&file_rwsem); spin_lock(&blocked_lock_lock); - return seq_hlist_start_percpu(&file_lock_list, &iter->li_cpu, *pos); + return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) @@ -2713,14 +2757,14 @@ static void *locks_next(struct seq_file *f, void *v, loff_t *pos) struct locks_iterator *iter = f->private; ++iter->li_pos; - return seq_hlist_next_percpu(v, &file_lock_list, &iter->li_cpu, pos); + return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) __releases(&blocked_lock_lock) { spin_unlock(&blocked_lock_lock); - lg_global_unlock(&file_lock_lglock); + percpu_up_write(&file_rwsem); } static const struct seq_operations locks_seq_operations = { @@ -2761,10 +2805,13 @@ static int __init filelock_init(void) filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); - lg_lock_init(&file_lock_lglock, "file_lock_lglock"); - for_each_possible_cpu(i) - INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i)); + for_each_possible_cpu(i) { + struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); + + spin_lock_init(&fll->lock); + INIT_HLIST_HEAD(&fll->hlist); + } return 0; } diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d2f97ecca6a5..e0e5f7c3c99f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response || - atomic_read(&group->fanotify_data.bypass_perm)); - - if (!event->response) { /* bypass_perm set */ - /* - * Event was canceled because group is being destroyed. Remove - * it from group's event list because we are responsible for - * freeing the permission event. - */ - fsnotify_remove_event(group, &event->fae.fse); - return 0; - } + wait_event(group->fanotify_data.access_waitq, event->response); /* userspace responded, convert to something usable */ switch (event->response) { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8e8e6bcd1d43..a64313868d3a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS struct fanotify_perm_event_info *event, *next; + struct fsnotify_event *fsn_event; /* - * There may be still new events arriving in the notification queue - * but since userspace cannot use fanotify fd anymore, no event can - * enter or leave access_list by now. + * Stop new events from arriving in the notification queue. since + * userspace cannot use fanotify fd anymore, no event can enter or + * leave access_list by now either. */ - spin_lock(&group->fanotify_data.access_lock); - - atomic_inc(&group->fanotify_data.bypass_perm); + fsnotify_group_stop_queueing(group); + /* + * Process all permission events on access_list and notification queue + * and simulate reply from userspace. + */ + spin_lock(&group->fanotify_data.access_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) spin_unlock(&group->fanotify_data.access_lock); /* - * Since bypass_perm is set, newly queued events will not wait for - * access response. Wake up the already sleeping ones now. - * synchronize_srcu() in fsnotify_destroy_group() will wait for all - * processes sleeping in fanotify_handle_event() waiting for access - * response and thus also for all permission events to be freed. + * Destroy all non-permission events. For permission events just + * dequeue them and set the response. They will be freed once the + * response is consumed and fanotify_get_response() returns. */ + mutex_lock(&group->notification_mutex); + while (!fsnotify_notify_queue_is_empty(group)) { + fsn_event = fsnotify_remove_first_event(group); + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + fsnotify_destroy_event(group, fsn_event); + else + FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + } + mutex_unlock(&group->notification_mutex); + + /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); #endif @@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/fs/notify/group.c b/fs/notify/group.c index 3e2dd85be5dd..b47f7cfdcaa4 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) } /* + * Stop queueing new events for this group. Once this function returns + * fsnotify_add_event() will not add any new events to the group's queue. + */ +void fsnotify_group_stop_queueing(struct fsnotify_group *group) +{ + mutex_lock(&group->notification_mutex); + group->shutdown = true; + mutex_unlock(&group->notification_mutex); +} + +/* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. * Note that another thread calling fsnotify_clear_marks_by_group() may still @@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_destroy_group(struct fsnotify_group *group) { + /* + * Stop queueing new events. The code below is careful enough to not + * require this but fanotify needs to stop queuing events even before + * fsnotify_destroy_group() is called and this makes the other callers + * of fsnotify_destroy_group() to see the same behavior. + */ + fsnotify_group_stop_queueing(group); + /* clear all inode marks for this group, attach them to destroy_list */ fsnotify_detach_group_marks(group); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index a95d8e037aeb..e455e83ceeeb 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was * added to the queue, 1 if the event was merged with some other queued event, - * 2 if the queue of events has overflown. + * 2 if the event was not queued - either the queue of events has overflown + * or the group is shutting down. */ int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); + if (group->shutdown) { + mutex_unlock(&group->notification_mutex); + return 2; + } + if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ @@ -126,21 +132,6 @@ queue: } /* - * Remove @event from group's notification queue. It is the responsibility of - * the caller to destroy the event. - */ -void fsnotify_remove_event(struct fsnotify_group *group, - struct fsnotify_event *event) -{ - mutex_lock(&group->notification_mutex); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - group->q_len--; - } - mutex_unlock(&group->notification_mutex); -} - -/* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event */ diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 7dabbc31060e..f165f867f332 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5922,7 +5922,6 @@ bail: } static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, - handle_t *handle, struct inode *data_alloc_inode, struct buffer_head *data_alloc_bh) { @@ -5935,11 +5934,19 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, struct ocfs2_truncate_log *tl; struct inode *tl_inode = osb->osb_tl_inode; struct buffer_head *tl_bh = osb->osb_tl_bh; + handle_t *handle; di = (struct ocfs2_dinode *) tl_bh->b_data; tl = &di->id2.i_dealloc; i = le16_to_cpu(tl->tl_used) - 1; while (i >= 0) { + handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); + if (IS_ERR(handle)) { + status = PTR_ERR(handle); + mlog_errno(status); + goto bail; + } + /* Caller has given us at least enough credits to * update the truncate log dinode */ status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh, @@ -5974,12 +5981,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, } } - status = ocfs2_extend_trans(handle, - OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); - if (status < 0) { - mlog_errno(status); - goto bail; - } + ocfs2_commit_trans(osb, handle); i--; } @@ -5994,7 +5996,6 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) { int status; unsigned int num_to_flush; - handle_t *handle; struct inode *tl_inode = osb->osb_tl_inode; struct inode *data_alloc_inode = NULL; struct buffer_head *tl_bh = osb->osb_tl_bh; @@ -6038,21 +6039,11 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) goto out_mutex; } - handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto out_unlock; - } - - status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode, + status = ocfs2_replay_truncate_records(osb, data_alloc_inode, data_alloc_bh); if (status < 0) mlog_errno(status); - ocfs2_commit_trans(osb, handle); - -out_unlock: brelse(data_alloc_bh); ocfs2_inode_unlock(data_alloc_inode, 1); @@ -6413,43 +6404,34 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb, goto out_mutex; } - handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - mlog_errno(ret); - goto out_unlock; - } - while (head) { if (head->free_bg) bg_blkno = head->free_bg; else bg_blkno = ocfs2_which_suballoc_group(head->free_blk, head->free_bit); + handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out_unlock; + } + trace_ocfs2_free_cached_blocks( (unsigned long long)head->free_blk, head->free_bit); ret = ocfs2_free_suballoc_bits(handle, inode, di_bh, head->free_bit, bg_blkno, 1); - if (ret) { + if (ret) mlog_errno(ret); - goto out_journal; - } - ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE); - if (ret) { - mlog_errno(ret); - goto out_journal; - } + ocfs2_commit_trans(osb, handle); tmp = head; head = head->free_next; kfree(tmp); } -out_journal: - ocfs2_commit_trans(osb, handle); - out_unlock: ocfs2_inode_unlock(inode, 1); brelse(di_bh); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 98d36548153d..bbb4b3e5b4ff 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1842,6 +1842,16 @@ out_commit: ocfs2_commit_trans(osb, handle); out: + /* + * The mmapped page won't be unlocked in ocfs2_free_write_ctxt(), + * even in case of error here like ENOSPC and ENOMEM. So, we need + * to unlock the target page manually to prevent deadlocks when + * retrying again on ENOSPC, or when returning non-VM_FAULT_LOCKED + * to VM code. + */ + if (wc->w_target_locked) + unlock_page(mmap_page); + ocfs2_free_write_ctxt(inode, wc); if (data_ac) { diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h index 94b18369b1cc..b95e7df5b76a 100644 --- a/fs/ocfs2/cluster/tcp_internal.h +++ b/fs/ocfs2/cluster/tcp_internal.h @@ -44,9 +44,6 @@ * version here in tcp_internal.h should not need to be bumped for * filesystem locking changes. * - * New in version 12 - * - Negotiate hb timeout when storage is down. - * * New in version 11 * - Negotiation of filesystem locking in the dlm join. * @@ -78,7 +75,7 @@ * - full 64 bit i_size in the metadata lock lvbs * - introduction of "rw" lock and pushing meta/data locking down */ -#define O2NET_PROTOCOL_VERSION 12ULL +#define O2NET_PROTOCOL_VERSION 11ULL struct o2net_handshake { __be64 protocol_version; __be64 connector_id; diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index cdeafb4e7ed6..0bb128659d4b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -268,7 +268,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; - u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -335,7 +334,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; - lock->convert_pending = 0; /* if it failed, move it back to granted queue. * if master returns DLM_NORMAL and then down before sending ast, * it may have already been moved to granted queue, reset to @@ -344,12 +342,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); - } else if ((res->state & DLM_LOCK_RES_RECOVERING) || - (old_owner != res->owner)) { - mlog(0, "res %.*s is in recovering or has been recovered.\n", - res->lockname.len, res->lockname.name); + } else if (!lock->convert_pending) { + mlog(0, "%s: res %.*s, owner died and lock has been moved back " + "to granted list, retry convert.\n", + dlm->name, res->lockname.len, res->lockname.name); status = DLM_RECOVERING; } + + lock->convert_pending = 0; bail: spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 4e7b0dc22450..0b055bfb8e86 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1506,7 +1506,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { int ret = 0; - u64 tmpend, end = start + len; + u64 tmpend = 0; + u64 end = start + len; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; @@ -1538,18 +1539,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, } /* - * We want to get the byte offset of the end of the 1st cluster. + * If start is on a cluster boundary and end is somewhere in another + * cluster, we have not COWed the cluster starting at start, unless + * end is also within the same cluster. So, in this case, we skip this + * first call to ocfs2_zero_range_for_truncate() truncate and move on + * to the next one. */ - tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1)); - if (tmpend > end) - tmpend = end; + if ((start & (csize - 1)) != 0) { + /* + * We want to get the byte offset of the end of the 1st + * cluster. + */ + tmpend = (u64)osb->s_clustersize + + (start & ~(osb->s_clustersize - 1)); + if (tmpend > end) + tmpend = end; - trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start, - (unsigned long long)tmpend); + trace_ocfs2_zero_partial_clusters_range1( + (unsigned long long)start, + (unsigned long long)tmpend); - ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend); - if (ret) - mlog_errno(ret); + ret = ocfs2_zero_range_for_truncate(inode, handle, start, + tmpend); + if (ret) + mlog_errno(ret); + } if (tmpend < end) { /* diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index ea47120a85ff..6ad3533940ba 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1199,14 +1199,24 @@ retry: inode_unlock((*ac)->ac_inode); ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted); - if (ret == 1) + if (ret == 1) { + iput((*ac)->ac_inode); + (*ac)->ac_inode = NULL; goto retry; + } if (ret < 0) mlog_errno(ret); inode_lock((*ac)->ac_inode); - ocfs2_inode_lock((*ac)->ac_inode, NULL, 1); + ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1); + if (ret < 0) { + mlog_errno(ret); + inode_unlock((*ac)->ac_inode); + iput((*ac)->ac_inode); + (*ac)->ac_inode = NULL; + goto bail; + } } if (status < 0) { if (status != -ENOSPC) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 43fdc2765aea..db37a0e02d32 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -105,6 +105,13 @@ retry: goto retry; } + error = security_inode_copy_up_xattr(name); + if (error < 0 && error != -EOPNOTSUPP) + break; + if (error == 1) { + error = 0; + continue; /* Discard */ + } error = vfs_setxattr(new, name, value, size, 0); if (error) break; @@ -248,6 +255,8 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, struct dentry *upper = NULL; umode_t mode = stat->mode; int err; + const struct cred *old_creds = NULL; + struct cred *new_creds = NULL; newdentry = ovl_lookup_temp(workdir, dentry); err = PTR_ERR(newdentry); @@ -260,10 +269,23 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, if (IS_ERR(upper)) goto out1; + err = security_inode_copy_up(dentry, &new_creds); + if (err < 0) + goto out2; + + if (new_creds) + old_creds = override_creds(new_creds); + /* Can't properly set mode on creation because of the umask */ stat->mode &= S_IFMT; err = ovl_create_real(wdir, newdentry, stat, link, NULL, true); stat->mode = mode; + + if (new_creds) { + revert_creds(old_creds); + put_cred(new_creds); + } + if (err) goto out2; diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 1560fdc09a5f..b0ffa1d1677e 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -489,6 +489,15 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, if (override_cred) { override_cred->fsuid = inode->i_uid; override_cred->fsgid = inode->i_gid; + if (!hardlink) { + err = security_dentry_create_files_as(dentry, + stat->mode, &dentry->d_name, old_cred, + override_cred); + if (err) { + put_cred(override_cred); + goto out_revert_creds; + } + } put_cred(override_creds(override_cred)); put_cred(override_cred); @@ -499,6 +508,7 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, err = ovl_create_over_whiteout(dentry, inode, stat, link, hardlink); } +out_revert_creds: revert_creds(old_cred); if (!err) { struct inode *realinode = d_inode(ovl_dentry_upper(dentry)); diff --git a/fs/proc/base.c b/fs/proc/base.c index ac0df4dde823..3b792ab3c0dc 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -483,7 +483,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, save_stack_trace_tsk(task, &trace); for (i = 0; i < trace.nr_entries; i++) { - seq_printf(m, "[<%pK>] %pS\n", + seq_printf(m, "[<%pK>] %pB\n", (void *)entries[i], (void *)entries[i]); } unlock_trace(task); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index c633476616e0..bca66d83a765 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -390,6 +390,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, atomic_set(&ent->count, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); + proc_set_user(ent, (*parent)->uid, (*parent)->gid); + out: return ent; } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index a939f5ed7f89..5c89a07e3d7f 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -430,6 +430,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) static ssize_t read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) { + char *buf = file->private_data; ssize_t acc = 0; size_t size, tsz; size_t elf_buflen; @@ -500,23 +501,20 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) if (clear_user(buffer, tsz)) return -EFAULT; } else if (is_vmalloc_or_module_addr((void *)start)) { - char * elf_buf; - - elf_buf = kzalloc(tsz, GFP_KERNEL); - if (!elf_buf) - return -ENOMEM; - vread(elf_buf, (char *)start, tsz); + vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ - if (copy_to_user(buffer, elf_buf, tsz)) { - kfree(elf_buf); + if (copy_to_user(buffer, buf, tsz)) return -EFAULT; - } - kfree(elf_buf); } else { if (kern_addr_valid(start)) { unsigned long n; - n = copy_to_user(buffer, (char *)start, tsz); + /* + * Using bounce buffer to bypass the + * hardened user copy kernel text checks. + */ + memcpy(buf, (char *) start, tsz); + n = copy_to_user(buffer, buf, tsz); /* * We cannot distinguish between fault on source * and fault on destination. When this happens @@ -549,6 +547,11 @@ static int open_kcore(struct inode *inode, struct file *filp) { if (!capable(CAP_SYS_RAWIO)) return -EPERM; + + filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!filp->private_data) + return -ENOMEM; + if (kcore_need_update) kcore_update_ram(); if (i_size_read(inode) != proc_root_kcore->size) { @@ -559,10 +562,16 @@ static int open_kcore(struct inode *inode, struct file *filp) return 0; } +static int release_kcore(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} static const struct file_operations proc_kcore_operations = { .read = read_kcore, .open = open_kcore, + .release = release_kcore, .llseek = default_llseek, }; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index c8bbc68cdb05..7ae6b1da7cab 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -21,6 +21,7 @@ #include <linux/bitops.h> #include <linux/mount.h> #include <linux/nsproxy.h> +#include <linux/uidgid.h> #include <net/net_namespace.h> #include <linux/seq_file.h> @@ -185,6 +186,8 @@ const struct file_operations proc_net_operations = { static __net_init int proc_net_ns_init(struct net *net) { struct proc_dir_entry *netd, *net_statd; + kuid_t uid; + kgid_t gid; int err; err = -ENOMEM; @@ -199,6 +202,16 @@ static __net_init int proc_net_ns_init(struct net *net) netd->parent = &proc_root; memcpy(netd->name, "net", 4); + uid = make_kuid(net->user_ns, 0); + if (!uid_valid(uid)) + uid = netd->uid; + + gid = make_kgid(net->user_ns, 0); + if (!gid_valid(gid)) + gid = netd->gid; + + proc_set_user(netd, uid, gid); + err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1b93650dda2f..2ed3d71d4767 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -430,6 +430,7 @@ static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, i static struct inode *proc_sys_make_inode(struct super_block *sb, struct ctl_table_header *head, struct ctl_table *table) { + struct ctl_table_root *root = head->root; struct inode *inode; struct proc_inode *ei; @@ -457,6 +458,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (is_empty_dir(head)) make_empty_dir_inode(inode); } + + if (root->set_ownership) + root->set_ownership(head, table, &inode->i_uid, &inode->i_gid); + out: return inode; } diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 35df08ee9c97..2d445425aad7 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -341,6 +341,7 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) struct qc_state state; int ret; + memset(&state, 0, sizeof (struct qc_state)); ret = sb->s_qcop->get_state(sb, &state); if (ret < 0) return ret; @@ -365,17 +366,19 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; - if (state.s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) { + + /* Inodes may be allocated even if inactive; copy out if present */ + if (state.s_state[USRQUOTA].ino) { fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; } - if (state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) { + if (state.s_state[GRPQUOTA].ino) { fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; } - if (state.s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) { + if (state.s_state[PRJQUOTA].ino) { /* * Q_XGETQSTAT doesn't have room for both group and project * quotas. So, allow the project quota values to be copied out @@ -411,6 +414,7 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) struct qc_state state; int ret; + memset(&state, 0, sizeof (struct qc_state)); ret = sb->s_qcop->get_state(sb, &state); if (ret < 0) return ret; @@ -435,17 +439,19 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; - if (state.s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) { + + /* Inodes may be allocated even if inactive; copy out if present */ + if (state.s_state[USRQUOTA].ino) { fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; } - if (state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) { + if (state.s_state[GRPQUOTA].ino) { fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; } - if (state.s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) { + if (state.s_state[PRJQUOTA].ino) { fqs->qs_pquota.qfs_ino = state.s_state[PRJQUOTA].ino; fqs->qs_pquota.qfs_nblks = state.s_state[PRJQUOTA].blocks; fqs->qs_pquota.qfs_nextents = state.s_state[PRJQUOTA].nextents; diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 183a212694bf..12af0490322f 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -27,9 +27,17 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/ramfs.h> +#include <linux/sched.h> #include "internal.h" +static unsigned long ramfs_mmu_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} + const struct file_operations ramfs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, @@ -38,6 +46,7 @@ const struct file_operations ramfs_file_operations = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, + .get_unmapped_area = ramfs_mmu_get_unmapped_area, }; const struct inode_operations ramfs_file_inode_operations = { diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 7a4a85a6821e..74d5ddd26296 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -190,7 +190,15 @@ static int remove_save_link_only(struct super_block *s, static int reiserfs_quota_on_mount(struct super_block *, int); #endif -/* look for uncompleted unlinks and truncates and complete them */ +/* + * Look for uncompleted unlinks and truncates and complete them + * + * Called with superblock write locked. If quotas are enabled, we have to + * release/retake lest we call dquot_quota_on_mount(), proceed to + * schedule_on_each_cpu() in invalidate_bdev() and deadlock waiting for the per + * cpu worklets to complete flush_async_commits() that in turn wait for the + * superblock write lock. + */ static int finish_unfinished(struct super_block *s) { INITIALIZE_PATH(path); @@ -237,7 +245,9 @@ static int finish_unfinished(struct super_block *s) quota_enabled[i] = 0; continue; } + reiserfs_write_unlock(s); ret = reiserfs_quota_on_mount(s, i); + reiserfs_write_lock(s); if (ret < 0) reiserfs_warning(s, "reiserfs-2500", "cannot turn on journaled " diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index dc1358b5ec95..ac2de0ed69ad 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -233,8 +233,8 @@ void sysfs_remove_group(struct kobject *kobj, kn = kernfs_find_and_get(parent, grp->name); if (!kn) { WARN(!kn, KERN_WARNING - "sysfs group %p not found for kobject '%s'\n", - grp, kobject_name(kobj)); + "sysfs group '%s' not found for kobject '%s'\n", + grp->name, kobject_name(kobj)); return; } } else { diff --git a/fs/udf/file.c b/fs/udf/file.c index 632570617327..e855bf8d74b4 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -94,7 +94,7 @@ static int udf_adinicb_write_begin(struct file *file, return -ENOMEM; *pagep = page; - if (!PageUptodate(page) && len != PAGE_SIZE) + if (!PageUptodate(page)) __udf_adinicb_readpage(page); return 0; } @@ -105,11 +105,25 @@ static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return 0; } +static int udf_adinicb_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + struct inode *inode = page->mapping->host; + loff_t last_pos = pos + copied; + if (last_pos > inode->i_size) + i_size_write(inode, last_pos); + set_page_dirty(page); + unlock_page(page); + put_page(page); + return copied; +} + const struct address_space_operations udf_adinicb_aops = { .readpage = udf_adinicb_readpage, .writepage = udf_adinicb_writepage, .write_begin = udf_adinicb_write_begin, - .write_end = simple_write_end, + .write_end = udf_adinicb_write_end, .direct_IO = udf_adinicb_direct_IO, }; |