diff options
Diffstat (limited to 'fs')
99 files changed, 2542 insertions, 1385 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index b3c2cc79c20d..082d227fa56b 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -277,6 +277,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, case ACL_TYPE_ACCESS: if (acl) { struct iattr iattr; + struct posix_acl *old_acl = acl; retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); if (retval) @@ -287,6 +288,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, * by the mode bits. So don't * update ACL. */ + posix_acl_release(old_acl); value = NULL; size = 0; } diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1e9d2f84e5b5..b29447e03ede 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -343,7 +343,7 @@ void afs_dispatch_give_up_callbacks(struct work_struct *work) * had callbacks entirely, and the server will call us later to break * them */ - afs_fs_give_up_callbacks(server, &afs_async_call); + afs_fs_give_up_callbacks(server, true); } /* diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index d764236072b1..2edbdcbf6432 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -24,65 +24,86 @@ 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 *); +static void SRXAFSCB_CallBack(struct work_struct *); +static void SRXAFSCB_InitCallBackState(struct work_struct *); +static void SRXAFSCB_Probe(struct work_struct *); +static void SRXAFSCB_ProbeUuid(struct work_struct *); +static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); + +#define CM_NAME(name) \ + const char afs_SRXCB##name##_name[] __tracepoint_string = \ + "CB." #name /* * CB.CallBack operation type */ +static CM_NAME(CallBack); static const struct afs_call_type afs_SRXCBCallBack = { - .name = "CB.CallBack", + .name = afs_SRXCBCallBack_name, .deliver = afs_deliver_cb_callback, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_CallBack, }; /* * CB.InitCallBackState operation type */ +static CM_NAME(InitCallBackState); static const struct afs_call_type afs_SRXCBInitCallBackState = { - .name = "CB.InitCallBackState", + .name = afs_SRXCBInitCallBackState_name, .deliver = afs_deliver_cb_init_call_back_state, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_InitCallBackState, }; /* * CB.InitCallBackState3 operation type */ +static CM_NAME(InitCallBackState3); static const struct afs_call_type afs_SRXCBInitCallBackState3 = { - .name = "CB.InitCallBackState3", + .name = afs_SRXCBInitCallBackState3_name, .deliver = afs_deliver_cb_init_call_back_state3, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_InitCallBackState, }; /* * CB.Probe operation type */ +static CM_NAME(Probe); static const struct afs_call_type afs_SRXCBProbe = { - .name = "CB.Probe", + .name = afs_SRXCBProbe_name, .deliver = afs_deliver_cb_probe, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_Probe, }; /* * CB.ProbeUuid operation type */ +static CM_NAME(ProbeUuid); static const struct afs_call_type afs_SRXCBProbeUuid = { - .name = "CB.ProbeUuid", + .name = afs_SRXCBProbeUuid_name, .deliver = afs_deliver_cb_probe_uuid, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_ProbeUuid, }; /* * CB.TellMeAboutYourself operation type */ +static CM_NAME(TellMeAboutYourself); static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { - .name = "CB.TellMeAboutYourself", + .name = afs_SRXCBTellMeAboutYourself_name, .deliver = afs_deliver_cb_tell_me_about_yourself, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_TellMeAboutYourself, }; /* @@ -153,6 +174,7 @@ static void SRXAFSCB_CallBack(struct work_struct *work) afs_send_empty_reply(call); afs_break_callbacks(call->server, call->count, call->request); + afs_put_call(call); _leave(""); } @@ -274,9 +296,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) return -ENOTCONN; call->server = server; - INIT_WORK(&call->work, SRXAFSCB_CallBack); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -290,6 +310,7 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) afs_init_callback_state(call->server); afs_send_empty_reply(call); + afs_put_call(call); _leave(""); } @@ -320,9 +341,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) return -ENOTCONN; call->server = server; - INIT_WORK(&call->work, SRXAFSCB_InitCallBackState); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -332,7 +351,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) { struct sockaddr_rxrpc srx; struct afs_server *server; - struct afs_uuid *r; + struct uuid_v1 *r; unsigned loop; __be32 *b; int ret; @@ -362,15 +381,15 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); + call->request = kmalloc(sizeof(struct uuid_v1), 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->time_low = b[0]; + r->time_mid = htons(ntohl(b[1])); + r->time_hi_and_version = htons(ntohl(b[2])); r->clock_seq_hi_and_reserved = ntohl(b[3]); r->clock_seq_low = ntohl(b[4]); @@ -394,9 +413,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) return -ENOTCONN; call->server = server; - INIT_WORK(&call->work, SRXAFSCB_InitCallBackState); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -408,6 +425,7 @@ static void SRXAFSCB_Probe(struct work_struct *work) _enter(""); afs_send_empty_reply(call); + afs_put_call(call); _leave(""); } @@ -427,9 +445,7 @@ static int afs_deliver_cb_probe(struct afs_call *call) /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; - INIT_WORK(&call->work, SRXAFSCB_Probe); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -438,7 +454,7 @@ static int afs_deliver_cb_probe(struct afs_call *call) static void SRXAFSCB_ProbeUuid(struct work_struct *work) { struct afs_call *call = container_of(work, struct afs_call, work); - struct afs_uuid *r = call->request; + struct uuid_v1 *r = call->request; struct { __be32 match; @@ -452,6 +468,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) reply.match = htonl(1); afs_send_simple_reply(call, &reply, sizeof(reply)); + afs_put_call(call); _leave(""); } @@ -460,7 +477,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) */ static int afs_deliver_cb_probe_uuid(struct afs_call *call) { - struct afs_uuid *r; + struct uuid_v1 *r; unsigned loop; __be32 *b; int ret; @@ -486,15 +503,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); + call->request = kmalloc(sizeof(struct uuid_v1), 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->time_low = b[0]; + r->time_mid = htons(ntohl(b[1])); + r->time_hi_and_version = htons(ntohl(b[2])); r->clock_seq_hi_and_reserved = ntohl(b[3]); r->clock_seq_low = ntohl(b[4]); @@ -510,9 +527,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) call->state = AFS_CALL_REPLYING; - INIT_WORK(&call->work, SRXAFSCB_ProbeUuid); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -554,9 +569,9 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) memset(&reply, 0, sizeof(reply)); reply.ia.nifs = htonl(nifs); - reply.ia.uuid[0] = htonl(afs_uuid.time_low); - reply.ia.uuid[1] = htonl(afs_uuid.time_mid); - reply.ia.uuid[2] = htonl(afs_uuid.time_hi_and_version); + reply.ia.uuid[0] = afs_uuid.time_low; + reply.ia.uuid[1] = htonl(ntohs(afs_uuid.time_mid)); + reply.ia.uuid[2] = htonl(ntohs(afs_uuid.time_hi_and_version)); reply.ia.uuid[3] = htonl((s8) afs_uuid.clock_seq_hi_and_reserved); reply.ia.uuid[4] = htonl((s8) afs_uuid.clock_seq_low); for (loop = 0; loop < 6; loop++) @@ -574,7 +589,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) reply.cap.capcount = htonl(1); reply.cap.caps[0] = htonl(AFS_CAP_ERROR_TRANSLATION); afs_send_simple_reply(call, &reply, sizeof(reply)); - + afs_put_call(call); _leave(""); } @@ -594,7 +609,5 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call) /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; - INIT_WORK(&call->work, SRXAFSCB_TellMeAboutYourself); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } diff --git a/fs/afs/file.c b/fs/afs/file.c index 6344aee4ac4b..ba7b71fba34b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -16,6 +16,7 @@ #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/gfp.h> +#include <linux/task_io_accounting_ops.h> #include "internal.h" static int afs_readpage(struct file *file, struct page *page); @@ -101,6 +102,21 @@ int afs_release(struct inode *inode, struct file *file) return 0; } +/* + * Dispose of a ref to a read record. + */ +void afs_put_read(struct afs_read *req) +{ + int i; + + if (atomic_dec_and_test(&req->usage)) { + for (i = 0; i < req->nr_pages; i++) + if (req->pages[i]) + put_page(req->pages[i]); + kfree(req); + } +} + #ifdef CONFIG_AFS_FSCACHE /* * deal with notification that a page was read from the cache @@ -126,9 +142,8 @@ int afs_page_filler(void *data, struct page *page) { struct inode *inode = page->mapping->host; struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_read *req; struct key *key = data; - size_t len; - off_t offset; int ret; _enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index); @@ -164,12 +179,23 @@ int afs_page_filler(void *data, struct page *page) _debug("cache said ENOBUFS"); default: go_on: - offset = page->index << PAGE_SHIFT; - len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE); + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), + GFP_KERNEL); + if (!req) + goto enomem; + + atomic_set(&req->usage, 1); + req->pos = (loff_t)page->index << PAGE_SHIFT; + req->len = min_t(size_t, i_size_read(inode) - req->pos, + PAGE_SIZE); + req->nr_pages = 1; + req->pages[0] = page; + get_page(page); /* read the contents of the file from the server into the * page */ - ret = afs_vnode_fetch_data(vnode, key, offset, len, page); + ret = afs_vnode_fetch_data(vnode, key, req); + afs_put_read(req); if (ret < 0) { if (ret == -ENOENT) { _debug("got NOENT from server" @@ -201,6 +227,8 @@ int afs_page_filler(void *data, struct page *page) _leave(" = 0"); return 0; +enomem: + ret = -ENOMEM; error: SetPageError(page); unlock_page(page); @@ -235,6 +263,131 @@ static int afs_readpage(struct file *file, struct page *page) } /* + * Make pages available as they're filled. + */ +static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req) +{ +#ifdef CONFIG_AFS_FSCACHE + struct afs_vnode *vnode = call->reply; +#endif + struct page *page = req->pages[req->index]; + + req->pages[req->index] = NULL; + SetPageUptodate(page); + + /* send the page to the cache */ +#ifdef CONFIG_AFS_FSCACHE + if (PageFsCache(page) && + fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) { + fscache_uncache_page(vnode->cache, page); + BUG_ON(PageFsCache(page)); + } +#endif + unlock_page(page); + put_page(page); +} + +/* + * Read a contiguous set of pages. + */ +static int afs_readpages_one(struct file *file, struct address_space *mapping, + struct list_head *pages) +{ + struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct afs_read *req; + struct list_head *p; + struct page *first, *page; + struct key *key = file->private_data; + pgoff_t index; + int ret, n, i; + + /* Count the number of contiguous pages at the front of the list. Note + * that the list goes prev-wards rather than next-wards. + */ + first = list_entry(pages->prev, struct page, lru); + index = first->index + 1; + n = 1; + for (p = first->lru.prev; p != pages; p = p->prev) { + page = list_entry(p, struct page, lru); + if (page->index != index) + break; + index++; + n++; + } + + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *) * n, + GFP_NOFS); + if (!req) + return -ENOMEM; + + atomic_set(&req->usage, 1); + req->page_done = afs_readpages_page_done; + req->pos = first->index; + req->pos <<= PAGE_SHIFT; + + /* Transfer the pages to the request. We add them in until one fails + * to add to the LRU and then we stop (as that'll make a hole in the + * contiguous run. + * + * Note that it's possible for the file size to change whilst we're + * doing this, but we rely on the server returning less than we asked + * for if the file shrank. We also rely on this to deal with a partial + * page at the end of the file. + */ + do { + page = list_entry(pages->prev, struct page, lru); + list_del(&page->lru); + index = page->index; + if (add_to_page_cache_lru(page, mapping, index, + readahead_gfp_mask(mapping))) { +#ifdef CONFIG_AFS_FSCACHE + fscache_uncache_page(vnode->cache, page); +#endif + put_page(page); + break; + } + + req->pages[req->nr_pages++] = page; + req->len += PAGE_SIZE; + } while (req->nr_pages < n); + + if (req->nr_pages == 0) { + kfree(req); + return 0; + } + + ret = afs_vnode_fetch_data(vnode, key, req); + if (ret < 0) + goto error; + + task_io_account_read(PAGE_SIZE * req->nr_pages); + afs_put_read(req); + return 0; + +error: + if (ret == -ENOENT) { + _debug("got NOENT from server" + " - marking file deleted and stale"); + set_bit(AFS_VNODE_DELETED, &vnode->flags); + ret = -ESTALE; + } + + for (i = 0; i < req->nr_pages; i++) { + page = req->pages[i]; + if (page) { +#ifdef CONFIG_AFS_FSCACHE + fscache_uncache_page(vnode->cache, page); +#endif + SetPageError(page); + unlock_page(page); + } + } + + afs_put_read(req); + return ret; +} + +/* * read a set of pages */ static int afs_readpages(struct file *file, struct address_space *mapping, @@ -287,8 +440,11 @@ static int afs_readpages(struct file *file, struct address_space *mapping, return ret; } - /* load the missing pages from the network */ - ret = read_cache_pages(mapping, pages, afs_page_filler, key); + while (!list_empty(pages)) { + ret = afs_readpages_one(file, mapping, pages); + if (ret < 0) + break; + } _leave(" = %d [netting]", ret); return ret; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 31c616ab9b40..ac8e766978dc 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -275,7 +275,7 @@ int afs_fs_fetch_file_status(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct afs_volsync *volsync, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -300,7 +300,7 @@ int afs_fs_fetch_file_status(struct afs_server *server, bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -309,15 +309,19 @@ int afs_fs_fetch_file_status(struct afs_server *server, static int afs_deliver_fs_fetch_data(struct afs_call *call) { struct afs_vnode *vnode = call->reply; + struct afs_read *req = call->reply3; const __be32 *bp; - struct page *page; + unsigned int size; void *buffer; int ret; - _enter("{%u}", call->unmarshall); + _enter("{%u,%zu/%u;%u/%llu}", + call->unmarshall, call->offset, call->count, + req->remain, req->actual_len); switch (call->unmarshall) { case 0: + req->actual_len = 0; call->offset = 0; call->unmarshall++; if (call->operation_ID != FSFETCHDATA64) { @@ -334,10 +338,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (ret < 0) return ret; - call->count = ntohl(call->tmp); - _debug("DATA length MSW: %u", call->count); - if (call->count > 0) - return -EBADMSG; + req->actual_len = ntohl(call->tmp); + req->actual_len <<= 32; call->offset = 0; call->unmarshall++; @@ -349,26 +351,52 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (ret < 0) return ret; - call->count = ntohl(call->tmp); - _debug("DATA length: %u", call->count); - if (call->count > PAGE_SIZE) + req->actual_len |= ntohl(call->tmp); + _debug("DATA length: %llu", req->actual_len); + /* Check that the server didn't want to send us extra. We + * might want to just discard instead, but that requires + * cooperation from AF_RXRPC. + */ + if (req->actual_len > req->len) return -EBADMSG; - call->offset = 0; + + req->remain = req->actual_len; + call->offset = req->pos & (PAGE_SIZE - 1); + req->index = 0; + if (req->actual_len == 0) + goto no_more_data; call->unmarshall++; + begin_page: + if (req->remain > PAGE_SIZE - call->offset) + size = PAGE_SIZE - call->offset; + else + size = req->remain; + call->count = call->offset + size; + ASSERTCMP(call->count, <=, PAGE_SIZE); + req->remain -= size; + /* extract the returned data */ case 3: - _debug("extract data"); - if (call->count > 0) { - page = call->reply3; - buffer = kmap(page); - ret = afs_extract_data(call, buffer, - call->count, true); - kunmap(page); - if (ret < 0) - return ret; + _debug("extract data %u/%llu %zu/%u", + req->remain, req->actual_len, call->offset, call->count); + + buffer = kmap(req->pages[req->index]); + ret = afs_extract_data(call, buffer, call->count, true); + kunmap(req->pages[req->index]); + if (ret < 0) + return ret; + if (call->offset == PAGE_SIZE) { + if (req->page_done) + req->page_done(call, req); + if (req->remain > 0) { + req->index++; + call->offset = 0; + goto begin_page; + } } + no_more_data: call->offset = 0; call->unmarshall++; @@ -393,17 +421,25 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) } if (call->count < PAGE_SIZE) { - _debug("clear"); - page = call->reply3; - buffer = kmap(page); + buffer = kmap(req->pages[req->index]); memset(buffer + call->count, 0, PAGE_SIZE - call->count); - kunmap(page); + kunmap(req->pages[req->index]); + if (req->page_done) + req->page_done(call, req); } _leave(" = 0 [done]"); return 0; } +static void afs_fetch_data_destructor(struct afs_call *call) +{ + struct afs_read *req = call->reply3; + + afs_put_read(req); + afs_flat_call_destructor(call); +} + /* * FS.FetchData operation type */ @@ -411,14 +447,14 @@ static const struct afs_call_type afs_RXFSFetchData = { .name = "FS.FetchData", .deliver = afs_deliver_fs_fetch_data, .abort_to_error = afs_abort_to_error, - .destructor = afs_flat_call_destructor, + .destructor = afs_fetch_data_destructor, }; static const struct afs_call_type afs_RXFSFetchData64 = { .name = "FS.FetchData64", .deliver = afs_deliver_fs_fetch_data, .abort_to_error = afs_abort_to_error, - .destructor = afs_flat_call_destructor, + .destructor = afs_fetch_data_destructor, }; /* @@ -427,17 +463,14 @@ static const struct afs_call_type afs_RXFSFetchData64 = { static int afs_fs_fetch_data64(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - off_t offset, size_t length, - struct page *buffer, - const struct afs_wait_mode *wait_mode) + struct afs_read *req, + bool async) { struct afs_call *call; __be32 *bp; _enter(""); - ASSERTCMP(length, <, ULONG_MAX); - call = afs_alloc_flat_call(&afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4); if (!call) return -ENOMEM; @@ -445,7 +478,7 @@ static int afs_fs_fetch_data64(struct afs_server *server, call->key = key; call->reply = vnode; call->reply2 = NULL; /* volsync */ - call->reply3 = buffer; + call->reply3 = req; call->service_id = FS_SERVICE; call->port = htons(AFS_FS_PORT); call->operation_ID = FSFETCHDATA64; @@ -456,12 +489,13 @@ static int afs_fs_fetch_data64(struct afs_server *server, bp[1] = htonl(vnode->fid.vid); bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - bp[4] = htonl(upper_32_bits(offset)); - bp[5] = htonl((u32) offset); + bp[4] = htonl(upper_32_bits(req->pos)); + bp[5] = htonl(lower_32_bits(req->pos)); bp[6] = 0; - bp[7] = htonl((u32) length); + bp[7] = htonl(lower_32_bits(req->len)); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + atomic_inc(&req->usage); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -470,16 +504,16 @@ static int afs_fs_fetch_data64(struct afs_server *server, int afs_fs_fetch_data(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - off_t offset, size_t length, - struct page *buffer, - const struct afs_wait_mode *wait_mode) + struct afs_read *req, + bool async) { struct afs_call *call; __be32 *bp; - if (upper_32_bits(offset) || upper_32_bits(offset + length)) - return afs_fs_fetch_data64(server, key, vnode, offset, length, - buffer, wait_mode); + if (upper_32_bits(req->pos) || + upper_32_bits(req->len) || + upper_32_bits(req->pos + req->len)) + return afs_fs_fetch_data64(server, key, vnode, req, async); _enter(""); @@ -490,7 +524,7 @@ int afs_fs_fetch_data(struct afs_server *server, call->key = key; call->reply = vnode; call->reply2 = NULL; /* volsync */ - call->reply3 = buffer; + call->reply3 = req; call->service_id = FS_SERVICE; call->port = htons(AFS_FS_PORT); call->operation_ID = FSFETCHDATA; @@ -501,10 +535,11 @@ int afs_fs_fetch_data(struct afs_server *server, bp[1] = htonl(vnode->fid.vid); bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - bp[4] = htonl(offset); - bp[5] = htonl(length); + bp[4] = htonl(lower_32_bits(req->pos)); + bp[5] = htonl(lower_32_bits(req->len)); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + atomic_inc(&req->usage); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -533,7 +568,7 @@ static const struct afs_call_type afs_RXFSGiveUpCallBacks = { * - the callbacks are held in the server->cb_break ring */ int afs_fs_give_up_callbacks(struct afs_server *server, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t ncallbacks; @@ -587,7 +622,7 @@ int afs_fs_give_up_callbacks(struct afs_server *server, ASSERT(ncallbacks > 0); wake_up_nr(&server->cb_break_waitq, ncallbacks); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -638,7 +673,7 @@ int afs_fs_create(struct afs_server *server, struct afs_fid *newfid, struct afs_file_status *newstatus, struct afs_callback *newcb, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz; @@ -683,7 +718,7 @@ int afs_fs_create(struct afs_server *server, *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ *bp++ = 0; /* segment size */ - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -728,7 +763,7 @@ int afs_fs_remove(struct afs_server *server, struct afs_vnode *vnode, const char *name, bool isdir, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz; @@ -763,7 +798,7 @@ int afs_fs_remove(struct afs_server *server, bp = (void *) bp + padsz; } - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -809,7 +844,7 @@ int afs_fs_link(struct afs_server *server, struct afs_vnode *dvnode, struct afs_vnode *vnode, const char *name, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz; @@ -848,7 +883,7 @@ int afs_fs_link(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -897,7 +932,7 @@ int afs_fs_symlink(struct afs_server *server, const char *contents, struct afs_fid *newfid, struct afs_file_status *newstatus, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz, c_namesz, c_padsz; @@ -952,7 +987,7 @@ int afs_fs_symlink(struct afs_server *server, *bp++ = htonl(S_IRWXUGO); /* unix mode */ *bp++ = 0; /* segment size */ - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1001,7 +1036,7 @@ int afs_fs_rename(struct afs_server *server, const char *orig_name, struct afs_vnode *new_dvnode, const char *new_name, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz; @@ -1055,7 +1090,7 @@ int afs_fs_rename(struct afs_server *server, bp = (void *) bp + n_padsz; } - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1110,7 +1145,7 @@ static int afs_fs_store_data64(struct afs_server *server, pgoff_t first, pgoff_t last, unsigned offset, unsigned to, loff_t size, loff_t pos, loff_t i_size, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_vnode *vnode = wb->vnode; struct afs_call *call; @@ -1159,7 +1194,7 @@ static int afs_fs_store_data64(struct afs_server *server, *bp++ = htonl(i_size >> 32); *bp++ = htonl((u32) i_size); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1168,7 +1203,7 @@ static int afs_fs_store_data64(struct afs_server *server, int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, pgoff_t first, pgoff_t last, unsigned offset, unsigned to, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_vnode *vnode = wb->vnode; struct afs_call *call; @@ -1194,7 +1229,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32) return afs_fs_store_data64(server, wb, first, last, offset, to, - size, pos, i_size, wait_mode); + size, pos, i_size, async); call = afs_alloc_flat_call(&afs_RXFSStoreData, (4 + 6 + 3) * 4, @@ -1233,7 +1268,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, *bp++ = htonl(size); *bp++ = htonl(i_size); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1295,7 +1330,7 @@ static const struct afs_call_type afs_RXFSStoreData64_as_Status = { */ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct iattr *attr, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1334,7 +1369,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, *bp++ = htonl(attr->ia_size >> 32); /* new file length */ *bp++ = htonl((u32) attr->ia_size); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1343,7 +1378,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, */ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct iattr *attr, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1354,7 +1389,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, ASSERT(attr->ia_valid & ATTR_SIZE); if (attr->ia_size >> 32) return afs_fs_setattr_size64(server, key, vnode, attr, - wait_mode); + async); call = afs_alloc_flat_call(&afs_RXFSStoreData_as_Status, (4 + 6 + 3) * 4, @@ -1382,7 +1417,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, *bp++ = 0; /* size of write */ *bp++ = htonl(attr->ia_size); /* new file length */ - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1391,14 +1426,14 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, */ int afs_fs_setattr(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct iattr *attr, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; if (attr->ia_valid & ATTR_SIZE) return afs_fs_setattr_size(server, key, vnode, attr, - wait_mode); + async); _enter(",%x,{%x:%u},,", key_serial(key), vnode->fid.vid, vnode->fid.vnode); @@ -1424,7 +1459,7 @@ int afs_fs_setattr(struct afs_server *server, struct key *key, xdr_encode_AFS_StoreStatus(&bp, attr); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1626,7 +1661,7 @@ int afs_fs_get_volume_status(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct afs_volume_status *vs, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1656,7 +1691,7 @@ int afs_fs_get_volume_status(struct afs_server *server, bp[0] = htonl(FSGETVOLUMESTATUS); bp[1] = htonl(vnode->fid.vid); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1718,7 +1753,7 @@ int afs_fs_set_lock(struct afs_server *server, struct key *key, struct afs_vnode *vnode, afs_lock_type_t type, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1742,7 +1777,7 @@ int afs_fs_set_lock(struct afs_server *server, *bp++ = htonl(vnode->fid.unique); *bp++ = htonl(type); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1751,7 +1786,7 @@ int afs_fs_set_lock(struct afs_server *server, int afs_fs_extend_lock(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1774,7 +1809,7 @@ int afs_fs_extend_lock(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1783,7 +1818,7 @@ int afs_fs_extend_lock(struct afs_server *server, int afs_fs_release_lock(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1806,5 +1841,5 @@ int afs_fs_release_lock(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 535a38d2c1d0..8acf3670e756 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -19,6 +19,7 @@ #include <linux/sched.h> #include <linux/fscache.h> #include <linux/backing-dev.h> +#include <linux/uuid.h> #include <net/af_rxrpc.h> #include "afs.h" @@ -51,31 +52,22 @@ struct afs_mount_params { struct key *key; /* key to use for secure mounting */ }; -/* - * definition of how to wait for the completion of an operation - */ -struct afs_wait_mode { - /* RxRPC received message notification */ - rxrpc_notify_rx_t notify_rx; - - /* synchronous call waiter and call dispatched notification */ - int (*wait)(struct afs_call *call); - - /* asynchronous call completion */ - void (*async_complete)(void *reply, int error); +enum afs_call_state { + AFS_CALL_REQUESTING, /* request is being sent for outgoing call */ + AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */ + AFS_CALL_AWAIT_OP_ID, /* awaiting op ID on incoming 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, /* Completed or failed */ }; - -extern const struct afs_wait_mode afs_sync_call; -extern const struct afs_wait_mode afs_async_call; - /* * a record of an in-progress RxRPC call */ 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 */ - struct work_struct async_work; /* asynchronous work processor */ + struct work_struct async_work; /* async I/O processor */ struct work_struct work; /* actual work processor */ struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ @@ -91,15 +83,8 @@ struct afs_call { 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 */ - AFS_CALL_AWAIT_OP_ID, /* awaiting op ID on incoming 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, /* Completed or failed */ - } state; + atomic_t usage; + enum afs_call_state state; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ unsigned request_size; /* size of request data */ @@ -110,6 +95,7 @@ struct afs_call { 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 */ + bool async; /* T if asynchronous */ u16 service_id; /* RxRPC service ID to call */ __be16 port; /* target UDP port */ u32 operation_ID; /* operation ID for an incoming call */ @@ -131,6 +117,25 @@ struct afs_call_type { /* clean up a call */ void (*destructor)(struct afs_call *call); + + /* Work function */ + void (*work)(struct work_struct *work); +}; + +/* + * Record of an outstanding read operation on a vnode. + */ +struct afs_read { + loff_t pos; /* Where to start reading */ + loff_t len; /* How much to read */ + loff_t actual_len; /* How much we're actually getting */ + atomic_t usage; + unsigned int remain; /* Amount remaining */ + unsigned int index; /* Which page we're reading into */ + unsigned int pg_offset; /* Offset in page we're at */ + unsigned int nr_pages; + void (*page_done)(struct afs_call *, struct afs_read *); + struct page *pages[]; }; /* @@ -403,30 +408,6 @@ struct afs_interface { unsigned mtu; /* MTU of interface */ }; -/* - * UUID definition [internet draft] - * - the timestamp is a 60-bit value, split 32/16/12, and goes in 100ns - * increments since midnight 15th October 1582 - * - add AFS_UUID_TO_UNIX_TIME to convert unix time in 100ns units to UUID - * time - * - the clock sequence is a 14-bit counter to avoid duplicate times - */ -struct afs_uuid { - u32 time_low; /* low part of timestamp */ - u16 time_mid; /* mid part of timestamp */ - u16 time_hi_and_version; /* high part of timestamp and version */ -#define AFS_UUID_TO_UNIX_TIME 0x01b21dd213814000ULL -#define AFS_UUID_TIMEHI_MASK 0x0fff -#define AFS_UUID_VERSION_TIME 0x1000 /* time-based UUID */ -#define AFS_UUID_VERSION_NAME 0x3000 /* name-based UUID */ -#define AFS_UUID_VERSION_RANDOM 0x4000 /* (pseudo-)random generated UUID */ - u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ -#define AFS_UUID_CLOCKHI_MASK 0x3f -#define AFS_UUID_VARIANT_STD 0x80 - u8 clock_seq_low; /* clock seq low */ - u8 node[6]; /* spatially unique node ID (MAC addr) */ -}; - /*****************************************************************************/ /* * cache.c @@ -494,6 +475,7 @@ extern const struct file_operations afs_file_operations; extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); extern int afs_page_filler(void *, struct page *); +extern void afs_put_read(struct afs_read *); /* * flock.c @@ -509,50 +491,37 @@ extern int afs_flock(struct file *, int, struct file_lock *); */ extern int afs_fs_fetch_file_status(struct afs_server *, struct key *, struct afs_vnode *, struct afs_volsync *, - const struct afs_wait_mode *); -extern int afs_fs_give_up_callbacks(struct afs_server *, - const struct afs_wait_mode *); + bool); +extern int afs_fs_give_up_callbacks(struct afs_server *, bool); extern int afs_fs_fetch_data(struct afs_server *, struct key *, - struct afs_vnode *, off_t, size_t, struct page *, - const struct afs_wait_mode *); + struct afs_vnode *, struct afs_read *, bool); extern int afs_fs_create(struct afs_server *, struct key *, struct afs_vnode *, const char *, umode_t, struct afs_fid *, struct afs_file_status *, - struct afs_callback *, - const struct afs_wait_mode *); + struct afs_callback *, bool); extern int afs_fs_remove(struct afs_server *, struct key *, - struct afs_vnode *, const char *, bool, - const struct afs_wait_mode *); + struct afs_vnode *, const char *, bool, bool); extern int afs_fs_link(struct afs_server *, struct key *, struct afs_vnode *, - struct afs_vnode *, const char *, - const struct afs_wait_mode *); + struct afs_vnode *, const char *, bool); extern int afs_fs_symlink(struct afs_server *, struct key *, struct afs_vnode *, const char *, const char *, - struct afs_fid *, struct afs_file_status *, - const struct afs_wait_mode *); + struct afs_fid *, struct afs_file_status *, bool); extern int afs_fs_rename(struct afs_server *, struct key *, struct afs_vnode *, const char *, - struct afs_vnode *, const char *, - const struct afs_wait_mode *); + struct afs_vnode *, const char *, bool); extern int afs_fs_store_data(struct afs_server *, struct afs_writeback *, - pgoff_t, pgoff_t, unsigned, unsigned, - const struct afs_wait_mode *); + pgoff_t, pgoff_t, unsigned, unsigned, bool); extern int afs_fs_setattr(struct afs_server *, struct key *, - struct afs_vnode *, struct iattr *, - const struct afs_wait_mode *); + struct afs_vnode *, struct iattr *, bool); extern int afs_fs_get_volume_status(struct afs_server *, struct key *, struct afs_vnode *, - struct afs_volume_status *, - const struct afs_wait_mode *); + struct afs_volume_status *, bool); extern int afs_fs_set_lock(struct afs_server *, struct key *, - struct afs_vnode *, afs_lock_type_t, - const struct afs_wait_mode *); + struct afs_vnode *, afs_lock_type_t, bool); extern int afs_fs_extend_lock(struct afs_server *, struct key *, - struct afs_vnode *, - const struct afs_wait_mode *); + struct afs_vnode *, bool); extern int afs_fs_release_lock(struct afs_server *, struct key *, - struct afs_vnode *, - const struct afs_wait_mode *); + struct afs_vnode *, bool); /* * inode.c @@ -573,7 +542,7 @@ extern int afs_drop_inode(struct inode *); * main.c */ extern struct workqueue_struct *afs_wq; -extern struct afs_uuid afs_uuid; +extern struct uuid_v1 afs_uuid; /* * misc.c @@ -592,6 +561,11 @@ extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *); extern void afs_mntpt_kill_timer(void); /* + * netdevices.c + */ +extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); + +/* * proc.c */ extern int afs_proc_init(void); @@ -603,11 +577,13 @@ extern void afs_proc_cell_remove(struct afs_cell *); * rxrpc.c */ extern struct socket *afs_socket; +extern atomic_t afs_outstanding_calls; extern int afs_open_socket(void); extern void afs_close_socket(void); -extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, - const struct afs_wait_mode *); +extern void afs_put_call(struct afs_call *); +extern int afs_queue_call_work(struct afs_call *); +extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, bool); 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 *); @@ -653,21 +629,14 @@ extern int afs_fs_init(void); extern void afs_fs_exit(void); /* - * use-rtnetlink.c - */ -extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); -extern int afs_get_MAC_address(u8 *, size_t); - -/* * vlclient.c */ extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *, const char *, struct afs_cache_vlocation *, - const struct afs_wait_mode *); + bool); extern int afs_vl_get_entry_by_id(struct in_addr *, struct key *, afs_volid_t, afs_voltype_t, - struct afs_cache_vlocation *, - const struct afs_wait_mode *); + struct afs_cache_vlocation *, bool); /* * vlocation.c @@ -699,7 +668,7 @@ extern void afs_vnode_finalise_status_update(struct afs_vnode *, extern int afs_vnode_fetch_status(struct afs_vnode *, struct afs_vnode *, struct key *); extern int afs_vnode_fetch_data(struct afs_vnode *, struct key *, - off_t, size_t, struct page *); + struct afs_read *); extern int afs_vnode_create(struct afs_vnode *, struct key *, const char *, umode_t, struct afs_fid *, struct afs_file_status *, struct afs_callback *, struct afs_server **); @@ -756,6 +725,8 @@ extern int afs_fsync(struct file *, loff_t, loff_t, int); /* * debug tracing */ +#include <trace/events/afs.h> + extern unsigned afs_debug; #define dbgprintk(FMT,...) \ diff --git a/fs/afs/main.c b/fs/afs/main.c index 0b187ef3b5b7..51d7d17bca57 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -15,6 +15,7 @@ #include <linux/completion.h> #include <linux/sched.h> #include <linux/random.h> +#define CREATE_TRACE_POINTS #include "internal.h" MODULE_DESCRIPTION("AFS Client File System"); @@ -30,53 +31,10 @@ static char *rootcell; module_param(rootcell, charp, 0); MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list"); -struct afs_uuid afs_uuid; +struct uuid_v1 afs_uuid; struct workqueue_struct *afs_wq; /* - * get a client UUID - */ -static int __init afs_get_client_UUID(void) -{ - struct timespec ts; - u64 uuidtime; - u16 clockseq; - int ret; - - /* read the MAC address of one of the external interfaces and construct - * a UUID from it */ - ret = afs_get_MAC_address(afs_uuid.node, sizeof(afs_uuid.node)); - if (ret < 0) - return ret; - - getnstimeofday(&ts); - uuidtime = (u64) ts.tv_sec * 1000 * 1000 * 10; - uuidtime += ts.tv_nsec / 100; - uuidtime += AFS_UUID_TO_UNIX_TIME; - afs_uuid.time_low = uuidtime; - afs_uuid.time_mid = uuidtime >> 32; - afs_uuid.time_hi_and_version = (uuidtime >> 48) & AFS_UUID_TIMEHI_MASK; - afs_uuid.time_hi_and_version |= AFS_UUID_VERSION_TIME; - - get_random_bytes(&clockseq, 2); - afs_uuid.clock_seq_low = clockseq; - afs_uuid.clock_seq_hi_and_reserved = - (clockseq >> 8) & AFS_UUID_CLOCKHI_MASK; - afs_uuid.clock_seq_hi_and_reserved |= AFS_UUID_VARIANT_STD; - - _debug("AFS UUID: %08x-%04x-%04x-%02x%02x-%02x%02x%02x%02x%02x%02x", - afs_uuid.time_low, - afs_uuid.time_mid, - afs_uuid.time_hi_and_version, - afs_uuid.clock_seq_hi_and_reserved, - afs_uuid.clock_seq_low, - afs_uuid.node[0], afs_uuid.node[1], afs_uuid.node[2], - afs_uuid.node[3], afs_uuid.node[4], afs_uuid.node[5]); - - return 0; -} - -/* * initialise the AFS client FS module */ static int __init afs_init(void) @@ -85,9 +43,7 @@ static int __init afs_init(void) printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 registering.\n"); - ret = afs_get_client_UUID(); - if (ret < 0) - return ret; + generate_random_uuid((unsigned char *)&afs_uuid); /* create workqueue */ ret = -ENOMEM; diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 81dd075356b9..d4fb0afc0097 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -202,7 +202,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) /* try and do the mount */ _debug("--- attempting mount %s -o %s ---", devname, options); - mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options); + mnt = vfs_submount(mntpt, &afs_fs_type, devname, options); _debug("--- mount result %p ---", mnt); free_page((unsigned long) devname); diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c index 7ad36506c256..40b2bab3e401 100644 --- a/fs/afs/netdevices.c +++ b/fs/afs/netdevices.c @@ -12,27 +12,6 @@ #include "internal.h" /* - * get a MAC address from a random ethernet interface that has a real one - * - the buffer will normally be 6 bytes in size - */ -int afs_get_MAC_address(u8 *mac, size_t maclen) -{ - struct net_device *dev; - int ret = -ENODEV; - - BUG_ON(maclen != ETH_ALEN); - - rtnl_lock(); - dev = __dev_getfirstbyhwtype(&init_net, ARPHRD_ETHER); - if (dev) { - memcpy(mac, dev->dev_addr, maclen); - ret = 0; - } - rtnl_unlock(); - return ret; -} - -/* * get a list of this system's interface IPv4 addresses, netmasks and MTUs * - maxbufs must be at least 1 * - returns the number of interface records in the buffer diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 25f05a8d21b1..95f42872b787 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -19,35 +19,16 @@ 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; +atomic_t afs_outstanding_calls; -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 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 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 = { - .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 = { - .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 = { - .notify_rx = afs_wake_up_async_call, -}; - /* asynchronous incoming call initial processing */ static const struct afs_call_type afs_RXCMxxxx = { .name = "CB.xxxx", @@ -130,9 +111,11 @@ void afs_close_socket(void) { _enter(""); + kernel_listen(afs_socket, 0); + flush_workqueue(afs_async_calls); + if (afs_spare_incoming_call) { - atomic_inc(&afs_outstanding_calls); - afs_free_call(afs_spare_incoming_call); + afs_put_call(afs_spare_incoming_call); afs_spare_incoming_call = NULL; } @@ -141,7 +124,6 @@ void afs_close_socket(void) 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); @@ -152,44 +134,79 @@ void afs_close_socket(void) } /* - * free a call + * Allocate a call. */ -static void afs_free_call(struct afs_call *call) +static struct afs_call *afs_alloc_call(const struct afs_call_type *type, + gfp_t gfp) { - _debug("DONE %p{%s} [%d]", - call, call->type->name, atomic_read(&afs_outstanding_calls)); + struct afs_call *call; + int o; - ASSERTCMP(call->rxcall, ==, NULL); - ASSERT(!work_pending(&call->async_work)); - ASSERT(call->type->name != NULL); + call = kzalloc(sizeof(*call), gfp); + if (!call) + return NULL; - kfree(call->request); - kfree(call); + call->type = type; + atomic_set(&call->usage, 1); + INIT_WORK(&call->async_work, afs_process_async_call); + init_waitqueue_head(&call->waitq); - if (atomic_dec_and_test(&afs_outstanding_calls)) - wake_up_atomic_t(&afs_outstanding_calls); + o = atomic_inc_return(&afs_outstanding_calls); + trace_afs_call(call, afs_call_trace_alloc, 1, o, + __builtin_return_address(0)); + return call; } /* - * End a call but do not free it + * Dispose of a reference on a call. */ -static void afs_end_call_nofree(struct afs_call *call) +void afs_put_call(struct afs_call *call) { - if (call->rxcall) { - rxrpc_kernel_end_call(afs_socket, call->rxcall); - call->rxcall = NULL; + int n = atomic_dec_return(&call->usage); + int o = atomic_read(&afs_outstanding_calls); + + trace_afs_call(call, afs_call_trace_put, n + 1, o, + __builtin_return_address(0)); + + ASSERTCMP(n, >=, 0); + if (n == 0) { + ASSERT(!work_pending(&call->async_work)); + ASSERT(call->type->name != NULL); + + if (call->rxcall) { + rxrpc_kernel_end_call(afs_socket, call->rxcall); + call->rxcall = NULL; + } + if (call->type->destructor) + call->type->destructor(call); + + kfree(call->request); + kfree(call); + + o = atomic_dec_return(&afs_outstanding_calls); + trace_afs_call(call, afs_call_trace_free, 0, o, + __builtin_return_address(0)); + if (o == 0) + wake_up_atomic_t(&afs_outstanding_calls); } - if (call->type->destructor) - call->type->destructor(call); } /* - * End a call and free it + * Queue the call for actual work. Returns 0 unconditionally for convenience. */ -static void afs_end_call(struct afs_call *call) +int afs_queue_call_work(struct afs_call *call) { - afs_end_call_nofree(call); - afs_free_call(call); + int u = atomic_inc_return(&call->usage); + + trace_afs_call(call, afs_call_trace_work, u, + atomic_read(&afs_outstanding_calls), + __builtin_return_address(0)); + + INIT_WORK(&call->work, call->type->work); + + if (!queue_work(afs_wq, &call->work)) + afs_put_call(call); + return 0; } /* @@ -200,25 +217,19 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, { struct afs_call *call; - call = kzalloc(sizeof(*call), GFP_NOFS); + call = afs_alloc_call(type, GFP_NOFS); if (!call) goto nomem_call; - _debug("CALL %p{%s} [%d]", - call, type->name, atomic_read(&afs_outstanding_calls)); - atomic_inc(&afs_outstanding_calls); - - call->type = type; - call->request_size = request_size; - call->reply_max = reply_max; - if (request_size) { + call->request_size = request_size; call->request = kmalloc(request_size, GFP_NOFS); if (!call->request) goto nomem_free; } if (reply_max) { + call->reply_max = reply_max; call->buffer = kmalloc(reply_max, GFP_NOFS); if (!call->buffer) goto nomem_free; @@ -228,7 +239,7 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, return call; nomem_free: - afs_free_call(call); + afs_put_call(call); nomem_call: return NULL; } @@ -315,7 +326,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, * initiate a call */ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, - const struct afs_wait_mode *wait_mode) + bool async) { struct sockaddr_rxrpc srx; struct rxrpc_call *rxcall; @@ -332,8 +343,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, call, call->type->name, key_serial(call->key), atomic_read(&afs_outstanding_calls)); - call->wait_mode = wait_mode; - INIT_WORK(&call->async_work, afs_process_async_call); + call->async = async; memset(&srx, 0, sizeof(srx)); srx.srx_family = AF_RXRPC; @@ -347,7 +357,9 @@ 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, - wait_mode->notify_rx); + (async ? + afs_wake_up_async_call : + afs_wake_up_call_waiter)); call->key = NULL; if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); @@ -386,12 +398,15 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, /* at this point, an async call may no longer exist as it may have * already completed */ - return wait_mode->wait(call); + if (call->async) + return -EINPROGRESS; + + return afs_wait_for_call_to_complete(call); error_do_abort: rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD"); error_kill_call: - afs_end_call(call); + afs_put_call(call); _leave(" = %d", ret); return ret; } @@ -416,6 +431,8 @@ static void afs_deliver_to_call(struct afs_call *call) ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, NULL, 0, &offset, false, &call->abort_code); + trace_afs_recv_data(call, 0, offset, false, ret); + if (ret == -EINPROGRESS || ret == -EAGAIN) return; if (ret == 1 || ret < 0) { @@ -459,7 +476,7 @@ static void afs_deliver_to_call(struct afs_call *call) done: if (call->state == AFS_CALL_COMPLETE && call->incoming) - afs_end_call(call); + afs_put_call(call); out: _leave(""); return; @@ -516,7 +533,7 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) } _debug("call complete"); - afs_end_call(call); + afs_put_call(call); _leave(" = %d", ret); return ret; } @@ -540,24 +557,25 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, unsigned long call_user_ID) { struct afs_call *call = (struct afs_call *)call_user_ID; + int u; + trace_afs_notify_call(rxcall, call); call->need_attention = true; - queue_work(afs_async_calls, &call->async_work); -} -/* - * put a call into asynchronous mode - * - mustn't touch the call descriptor as the call my have completed by the - * time we get here - */ -static int afs_dont_wait_for_call_to_complete(struct afs_call *call) -{ - _enter(""); - return -EINPROGRESS; + u = __atomic_add_unless(&call->usage, 1, 0); + if (u != 0) { + trace_afs_call(call, afs_call_trace_wake, u, + atomic_read(&afs_outstanding_calls), + __builtin_return_address(0)); + + if (!queue_work(afs_async_calls, &call->async_work)) + afs_put_call(call); + } } /* - * delete an asynchronous call + * Delete an asynchronous call. The work item carries a ref to the call struct + * that we need to release. */ static void afs_delete_async_call(struct work_struct *work) { @@ -565,13 +583,14 @@ static void afs_delete_async_call(struct work_struct *work) _enter(""); - afs_free_call(call); + afs_put_call(call); _leave(""); } /* - * perform processing on an asynchronous call + * Perform I/O processing on an asynchronous call. The work item carries a ref + * to the call struct that we either need to release or to pass on. */ static void afs_process_async_call(struct work_struct *work) { @@ -584,21 +603,19 @@ static void afs_process_async_call(struct work_struct *work) afs_deliver_to_call(call); } - if (call->state == AFS_CALL_COMPLETE && call->wait_mode) { - if (call->wait_mode->async_complete) - call->wait_mode->async_complete(call->reply, - call->error); + if (call->state == AFS_CALL_COMPLETE) { call->reply = NULL; - /* kill the call */ - afs_end_call_nofree(call); - - /* we can't just delete the call because the work item may be - * queued */ + /* We have two refs to release - one from the alloc and one + * queued with the work item - and we can't just deallocate the + * call because the work item may be queued again. + */ call->async_work.func = afs_delete_async_call; - queue_work(afs_async_calls, &call->async_work); + if (!queue_work(afs_async_calls, &call->async_work)) + afs_put_call(call); } + afs_put_call(call); _leave(""); } @@ -618,15 +635,13 @@ static void afs_charge_preallocation(struct work_struct *work) for (;;) { if (!call) { - call = kzalloc(sizeof(struct afs_call), GFP_KERNEL); + call = afs_alloc_call(&afs_RXCMxxxx, GFP_KERNEL); if (!call) break; - 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); + call->async = true; call->state = AFS_CALL_AWAIT_OP_ID; + init_waitqueue_head(&call->waitq); } if (rxrpc_kernel_charge_accept(afs_socket, @@ -648,9 +663,8 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall, { struct afs_call *call = (struct afs_call *)user_call_ID; - atomic_inc(&afs_outstanding_calls); call->rxcall = NULL; - afs_free_call(call); + afs_put_call(call); } /* @@ -659,7 +673,6 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall, 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); } @@ -689,6 +702,8 @@ static int afs_deliver_cm_op_id(struct afs_call *call) if (!afs_cm_incoming_call(call)) return -ENOTSUPP; + trace_afs_cb_call(call); + /* pass responsibility for the remainer of this message off to the * cache manager op */ return call->type->deliver(call); @@ -721,7 +736,6 @@ void afs_send_empty_reply(struct afs_call *call) rxrpc_kernel_abort_call(afs_socket, call->rxcall, RX_USER_ABORT, ENOMEM, "KOO"); default: - afs_end_call(call); _leave(" [error]"); return; } @@ -760,7 +774,6 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) rxrpc_kernel_abort_call(afs_socket, call->rxcall, RX_USER_ABORT, ENOMEM, "KOO"); } - afs_end_call(call); _leave(" [error]"); } @@ -780,6 +793,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, buf, count, &call->offset, want_more, &call->abort_code); + trace_afs_recv_data(call, count, call->offset, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index 94bcd97d22b8..a5e4cc561b6c 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -147,7 +147,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr, struct key *key, const char *volname, struct afs_cache_vlocation *entry, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t volnamesz, reqsz, padsz; @@ -177,7 +177,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr, memset((void *) bp + volnamesz, 0, padsz); /* initiate the call */ - return afs_make_call(addr, call, GFP_KERNEL, wait_mode); + return afs_make_call(addr, call, GFP_KERNEL, async); } /* @@ -188,7 +188,7 @@ int afs_vl_get_entry_by_id(struct in_addr *addr, afs_volid_t volid, afs_voltype_t voltype, struct afs_cache_vlocation *entry, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -211,5 +211,5 @@ int afs_vl_get_entry_by_id(struct in_addr *addr, *bp = htonl(voltype); /* initiate the call */ - return afs_make_call(addr, call, GFP_KERNEL, wait_mode); + return afs_make_call(addr, call, GFP_KERNEL, async); } diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 45a86396fd2d..d7d8dd8c0b31 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -53,7 +53,7 @@ static int afs_vlocation_access_vl_by_name(struct afs_vlocation *vl, /* attempt to access the VL server */ ret = afs_vl_get_entry_by_name(&addr, key, vl->vldb.name, vldb, - &afs_sync_call); + false); switch (ret) { case 0: goto out; @@ -111,7 +111,7 @@ static int afs_vlocation_access_vl_by_id(struct afs_vlocation *vl, /* attempt to access the VL server */ ret = afs_vl_get_entry_by_id(&addr, key, volid, voltype, vldb, - &afs_sync_call); + false); switch (ret) { case 0: goto out; diff --git a/fs/afs/vnode.c b/fs/afs/vnode.c index 25cf4c3f4ff7..dcb956143c86 100644 --- a/fs/afs/vnode.c +++ b/fs/afs/vnode.c @@ -358,7 +358,7 @@ get_anyway: server, ntohl(server->addr.s_addr)); ret = afs_fs_fetch_file_status(server, key, vnode, NULL, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -393,7 +393,7 @@ no_server: * - TODO implement caching */ int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key, - off_t offset, size_t length, struct page *page) + struct afs_read *desc) { struct afs_server *server; int ret; @@ -420,8 +420,8 @@ int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_fetch_data(server, key, vnode, offset, length, - page, &afs_sync_call); + ret = afs_fs_fetch_data(server, key, vnode, desc, + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -477,7 +477,7 @@ int afs_vnode_create(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_create(server, key, vnode, name, mode, newfid, - newstatus, newcb, &afs_sync_call); + newstatus, newcb, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -533,7 +533,7 @@ int afs_vnode_remove(struct afs_vnode *vnode, struct key *key, const char *name, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_remove(server, key, vnode, name, isdir, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -595,7 +595,7 @@ int afs_vnode_link(struct afs_vnode *dvnode, struct afs_vnode *vnode, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_link(server, key, dvnode, vnode, name, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(dvnode, server, ret)); @@ -659,7 +659,7 @@ int afs_vnode_symlink(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_symlink(server, key, vnode, name, content, - newfid, newstatus, &afs_sync_call); + newfid, newstatus, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -729,7 +729,7 @@ int afs_vnode_rename(struct afs_vnode *orig_dvnode, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_rename(server, key, orig_dvnode, orig_name, - new_dvnode, new_name, &afs_sync_call); + new_dvnode, new_name, false); } while (!afs_volume_release_fileserver(orig_dvnode, server, ret)); @@ -795,7 +795,7 @@ int afs_vnode_store_data(struct afs_writeback *wb, pgoff_t first, pgoff_t last, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_store_data(server, wb, first, last, offset, to, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -847,7 +847,7 @@ int afs_vnode_setattr(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_setattr(server, key, vnode, attr, &afs_sync_call); + ret = afs_fs_setattr(server, key, vnode, attr, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -894,7 +894,7 @@ int afs_vnode_get_volume_status(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_get_volume_status(server, key, vnode, vs, &afs_sync_call); + ret = afs_fs_get_volume_status(server, key, vnode, vs, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -933,7 +933,7 @@ int afs_vnode_set_lock(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_set_lock(server, key, vnode, type, &afs_sync_call); + ret = afs_fs_set_lock(server, key, vnode, type, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -971,7 +971,7 @@ int afs_vnode_extend_lock(struct afs_vnode *vnode, struct key *key) _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_extend_lock(server, key, vnode, &afs_sync_call); + ret = afs_fs_extend_lock(server, key, vnode, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -1009,7 +1009,7 @@ int afs_vnode_release_lock(struct afs_vnode *vnode, struct key *key) _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_release_lock(server, key, vnode, &afs_sync_call); + ret = afs_fs_release_lock(server, key, vnode, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index d142a2449e65..546f9d01710b 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -106,6 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params) volume->cell = params->cell; volume->vid = vlocation->vldb.vid[params->type]; + volume->bdi.ra_pages = VM_MAX_READAHEAD*1024/PAGE_SIZE; ret = bdi_setup_and_register(&volume->bdi, "afs"); if (ret) goto error_bdi; diff --git a/fs/afs/write.c b/fs/afs/write.c index f865c3f05bea..c83c1a0e851f 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -86,19 +86,30 @@ void afs_put_writeback(struct afs_writeback *wb) static int afs_fill_page(struct afs_vnode *vnode, struct key *key, loff_t pos, struct page *page) { + struct afs_read *req; loff_t i_size; int ret; - int len; _enter(",,%llu", (unsigned long long)pos); + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), + GFP_KERNEL); + if (!req) + return -ENOMEM; + + atomic_set(&req->usage, 1); + req->pos = pos; + req->nr_pages = 1; + req->pages[0] = page; + i_size = i_size_read(&vnode->vfs_inode); if (pos + PAGE_SIZE > i_size) - len = i_size - pos; + req->len = i_size - pos; else - len = PAGE_SIZE; + req->len = PAGE_SIZE; - ret = afs_vnode_fetch_data(vnode, key, pos, len, page); + ret = afs_vnode_fetch_data(vnode, key, req); + afs_put_read(req); if (ret < 0) { if (ret == -ENOENT) { _debug("got NOENT from server" diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 1278335ce366..79fbd85db4ba 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -436,8 +436,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->dev = autofs4_get_dev(sbi); wq->ino = autofs4_get_ino(sbi); - wq->uid = current_real_cred()->uid; - wq->gid = current_real_cred()->gid; + wq->uid = current_cred()->uid; + wq->gid = current_cred()->gid; wq->pid = pid; wq->tgid = tgid; wq->status = -EINTR; /* Status return if interrupted */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index e7bf01373bc4..443a6f537d56 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -91,12 +91,18 @@ static struct linux_binfmt elf_format = { #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) -static int set_brk(unsigned long start, unsigned long end) +static int set_brk(unsigned long start, unsigned long end, int prot) { start = ELF_PAGEALIGN(start); end = ELF_PAGEALIGN(end); if (end > start) { - int error = vm_brk(start, end - start); + /* + * Map the last of the bss segment. + * If the header is requesting these pages to be + * executable, honour that (ppc32 needs this). + */ + int error = vm_brk_flags(start, end - start, + prot & PROT_EXEC ? VM_EXEC : 0); if (error) return error; } @@ -524,6 +530,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, unsigned long load_addr = 0; int load_addr_set = 0; unsigned long last_bss = 0, elf_bss = 0; + int bss_prot = 0; unsigned long error = ~0UL; unsigned long total_size; int i; @@ -606,8 +613,10 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, * elf_bss and last_bss is the bss section. */ k = load_addr + eppnt->p_vaddr + eppnt->p_memsz; - if (k > last_bss) + if (k > last_bss) { last_bss = k; + bss_prot = elf_prot; + } } } @@ -623,13 +632,14 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, /* * Next, align both the file and mem bss up to the page size, * since this is where elf_bss was just zeroed up to, and where - * last_bss will end after the vm_brk() below. + * last_bss will end after the vm_brk_flags() below. */ elf_bss = ELF_PAGEALIGN(elf_bss); last_bss = ELF_PAGEALIGN(last_bss); /* Finally, if there is still more bss to allocate, do it. */ if (last_bss > elf_bss) { - error = vm_brk(elf_bss, last_bss - elf_bss); + error = vm_brk_flags(elf_bss, last_bss - elf_bss, + bss_prot & PROT_EXEC ? VM_EXEC : 0); if (error) goto out; } @@ -674,6 +684,7 @@ static int load_elf_binary(struct linux_binprm *bprm) unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; unsigned long elf_bss, elf_brk; + int bss_prot = 0; int retval, i; unsigned long elf_entry; unsigned long interp_load_addr = 0; @@ -882,7 +893,8 @@ static int load_elf_binary(struct linux_binprm *bprm) before this one. Map anonymous pages, if needed, and clear the area. */ retval = set_brk(elf_bss + load_bias, - elf_brk + load_bias); + elf_brk + load_bias, + bss_prot); if (retval) goto out_free_dentry; nbyte = ELF_PAGEOFFSET(elf_bss); @@ -976,8 +988,10 @@ static int load_elf_binary(struct linux_binprm *bprm) if (end_data < k) end_data = k; k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz; - if (k > elf_brk) + if (k > elf_brk) { + bss_prot = elf_prot; elf_brk = k; + } } loc->elf_ex.e_entry += load_bias; @@ -993,7 +1007,7 @@ static int load_elf_binary(struct linux_binprm *bprm) * mapping in the interpreter, to make sure it doesn't wind * up getting placed where the bss needs to go. */ - retval = set_brk(elf_bss, elf_brk); + retval = set_brk(elf_bss, elf_brk, bss_prot); if (retval) goto out_free_dentry; if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) { diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index ec9dbbcca3b9..9156be545b0f 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -245,7 +245,8 @@ compose_mount_options_err: * @fullpath: full path in UNC format * @ref: server's referral */ -static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb, +static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt, + struct cifs_sb_info *cifs_sb, const char *fullpath, const struct dfs_info3_param *ref) { struct vfsmount *mnt; @@ -259,7 +260,7 @@ static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb, if (IS_ERR(mountdata)) return (struct vfsmount *)mountdata; - mnt = vfs_kern_mount(&cifs_fs_type, 0, devname, mountdata); + mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata); kfree(mountdata); kfree(devname); return mnt; @@ -334,7 +335,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) mnt = ERR_PTR(-EINVAL); break; } - mnt = cifs_dfs_do_refmount(cifs_sb, + mnt = cifs_dfs_do_refmount(mntpt, cifs_sb, full_path, referrals + i); cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n", __func__, referrals[i].node_name, mnt); @@ -35,6 +35,9 @@ #include <linux/iomap.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/fs_dax.h> + /* We choose 4096 entries - same as per-zone page wait tables */ #define DAX_WAIT_TABLE_BITS 12 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS) @@ -1079,7 +1082,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, */ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, - struct iomap_ops *ops) + const struct iomap_ops *ops) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; @@ -1127,7 +1130,7 @@ static int dax_fault_return(int error) * necessary locking for the page fault to proceed successfully. */ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, - struct iomap_ops *ops) + const struct iomap_ops *ops) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; @@ -1253,21 +1256,21 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault); */ #define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) -static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd, - struct vm_fault *vmf, unsigned long address, - struct iomap *iomap, loff_t pos, bool write, void **entryp) +static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, + loff_t pos, void **entryp) { - struct address_space *mapping = vma->vm_file->f_mapping; + struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct block_device *bdev = iomap->bdev; + struct inode *inode = mapping->host; struct blk_dax_ctl dax = { .sector = dax_iomap_sector(iomap, pos), .size = PMD_SIZE, }; long length = dax_map_atomic(bdev, &dax); - void *ret; + void *ret = NULL; if (length < 0) /* dax_map_atomic() failed */ - return VM_FAULT_FALLBACK; + goto fallback; if (length < PMD_SIZE) goto unmap_fallback; if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) @@ -1280,67 +1283,86 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd, ret = dax_insert_mapping_entry(mapping, vmf, *entryp, dax.sector, RADIX_DAX_PMD); if (IS_ERR(ret)) - return VM_FAULT_FALLBACK; + goto fallback; *entryp = ret; - return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write); + trace_dax_pmd_insert_mapping(inode, vmf, length, dax.pfn, ret); + return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, + dax.pfn, vmf->flags & FAULT_FLAG_WRITE); unmap_fallback: dax_unmap_atomic(bdev, &dax); +fallback: + trace_dax_pmd_insert_mapping_fallback(inode, vmf, length, + dax.pfn, ret); return VM_FAULT_FALLBACK; } -static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd, - struct vm_fault *vmf, unsigned long address, - struct iomap *iomap, void **entryp) +static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, + void **entryp) { - struct address_space *mapping = vma->vm_file->f_mapping; - unsigned long pmd_addr = address & PMD_MASK; + struct address_space *mapping = vmf->vma->vm_file->f_mapping; + unsigned long pmd_addr = vmf->address & PMD_MASK; + struct inode *inode = mapping->host; struct page *zero_page; + void *ret = NULL; spinlock_t *ptl; pmd_t pmd_entry; - void *ret; - zero_page = mm_get_huge_zero_page(vma->vm_mm); + zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm); if (unlikely(!zero_page)) - return VM_FAULT_FALLBACK; + goto fallback; ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0, RADIX_DAX_PMD | RADIX_DAX_HZP); if (IS_ERR(ret)) - return VM_FAULT_FALLBACK; + goto fallback; *entryp = ret; - ptl = pmd_lock(vma->vm_mm, pmd); - if (!pmd_none(*pmd)) { + ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); + if (!pmd_none(*(vmf->pmd))) { spin_unlock(ptl); - return VM_FAULT_FALLBACK; + goto fallback; } - pmd_entry = mk_pmd(zero_page, vma->vm_page_prot); + pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); - set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry); + set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); spin_unlock(ptl); + trace_dax_pmd_load_hole(inode, vmf, zero_page, ret); return VM_FAULT_NOPAGE; + +fallback: + trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret); + return VM_FAULT_FALLBACK; } -int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, unsigned int flags, struct iomap_ops *ops) +int dax_iomap_pmd_fault(struct vm_fault *vmf, const struct iomap_ops *ops) { + struct vm_area_struct *vma = vmf->vma; struct address_space *mapping = vma->vm_file->f_mapping; - unsigned long pmd_addr = address & PMD_MASK; - bool write = flags & FAULT_FLAG_WRITE; + unsigned long pmd_addr = vmf->address & PMD_MASK; + bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT; struct inode *inode = mapping->host; int result = VM_FAULT_FALLBACK; struct iomap iomap = { 0 }; pgoff_t max_pgoff, pgoff; - struct vm_fault vmf; void *entry; loff_t pos; int error; + /* + * Check whether offset isn't beyond end of file now. Caller is + * supposed to hold locks serializing us with truncate / punch hole so + * this is a reliable test. + */ + pgoff = linear_page_index(vma, pmd_addr); + max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT; + + trace_dax_pmd_fault(inode, vmf, max_pgoff, 0); + /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) goto fallback; @@ -1351,16 +1373,10 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((pmd_addr + PMD_SIZE) > vma->vm_end) goto fallback; - /* - * Check whether offset isn't beyond end of file now. Caller is - * supposed to hold locks serializing us with truncate / punch hole so - * this is a reliable test. - */ - pgoff = linear_page_index(vma, pmd_addr); - max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT; - - if (pgoff > max_pgoff) - return VM_FAULT_SIGBUS; + if (pgoff > max_pgoff) { + result = VM_FAULT_SIGBUS; + goto out; + } /* If the PMD would extend beyond the file size */ if ((pgoff | PG_PMD_COLOUR) > max_pgoff) @@ -1389,21 +1405,15 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (IS_ERR(entry)) goto finish_iomap; - vmf.pgoff = pgoff; - vmf.flags = flags; - vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO; - switch (iomap.type) { case IOMAP_MAPPED: - result = dax_pmd_insert_mapping(vma, pmd, &vmf, address, - &iomap, pos, write, &entry); + result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (WARN_ON_ONCE(write)) goto unlock_entry; - result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap, - &entry); + result = dax_pmd_load_hole(vmf, &iomap, &entry); break; default: WARN_ON_ONCE(1); @@ -1429,9 +1439,11 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, } fallback: if (result == VM_FAULT_FALLBACK) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, vmf->pmd, vmf->address); count_vm_event(THP_FAULT_FALLBACK); } +out: + trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result); return result; } EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 7fb1732a3630..7fd4ec4bb214 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -187,9 +187,9 @@ static const struct super_operations debugfs_super_operations = { static struct vfsmount *debugfs_automount(struct path *path) { - struct vfsmount *(*f)(void *); - f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata; - return f(d_inode(path->dentry)->i_private); + debugfs_automount_t f; + f = (debugfs_automount_t)path->dentry->d_fsdata; + return f(path->dentry, d_inode(path->dentry)->i_private); } static const struct dentry_operations debugfs_dops = { @@ -540,7 +540,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir); */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); diff --git a/fs/exec.c b/fs/exec.c index e57946610733..698a86094f76 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1426,12 +1426,8 @@ static void check_unsafe_exec(struct linux_binprm *bprm) struct task_struct *p = current, *t; unsigned n_fs; - if (p->ptrace) { - if (ptracer_capable(p, current_user_ns())) - bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP; - else - bprm->unsafe |= LSM_UNSAFE_PTRACE; - } + if (p->ptrace) + bprm->unsafe |= LSM_UNSAFE_PTRACE; /* * This isn't strictly necessary, but it makes it harder for LSMs to @@ -1479,7 +1475,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm) if (task_no_new_privs(current)) return; - inode = file_inode(bprm->file); + inode = bprm->file->f_path.dentry->d_inode; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 37e2be784ac7..5e64de9c5093 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -814,7 +814,7 @@ extern const struct file_operations ext2_file_operations; /* inode.c */ extern const struct address_space_operations ext2_aops; extern const struct address_space_operations ext2_nobh_aops; -extern struct iomap_ops ext2_iomap_ops; +extern const struct iomap_ops ext2_iomap_ops; /* namei.c */ extern const struct inode_operations ext2_dir_inode_operations; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index f073bfca694b..128cce540645 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -842,13 +842,13 @@ ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length, return 0; } -struct iomap_ops ext2_iomap_ops = { +const struct iomap_ops ext2_iomap_ops = { .iomap_begin = ext2_iomap_begin, .iomap_end = ext2_iomap_end, }; #else /* Define empty ops for !CONFIG_FS_DAX case to avoid ugly ifdefs */ -struct iomap_ops ext2_iomap_ops; +const struct iomap_ops ext2_iomap_ops; #endif /* CONFIG_FS_DAX */ int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 01d52b98f9a7..cee23b684f47 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3244,7 +3244,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) } } -extern struct iomap_ops ext4_iomap_ops; +extern const struct iomap_ops ext4_iomap_ops; #endif /* __KERNEL__ */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 87e11dfe3cde..13021a054fc0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -273,21 +273,20 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return result; } -static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags) +static int +ext4_dax_pmd_fault(struct vm_fault *vmf) { int result; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct super_block *sb = inode->i_sb; - bool write = flags & FAULT_FLAG_WRITE; + bool write = vmf->flags & FAULT_FLAG_WRITE; if (write) { sb_start_pagefault(sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); } down_read(&EXT4_I(inode)->i_mmap_sem); - result = dax_iomap_pmd_fault(vma, addr, pmd, flags, - &ext4_iomap_ops); + result = dax_iomap_pmd_fault(vmf, &ext4_iomap_ops); up_read(&EXT4_I(inode)->i_mmap_sem); if (write) sb_end_pagefault(sb); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f622d4a577e3..75212a6e69f8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3450,7 +3450,7 @@ orphan_del: return ret; } -struct iomap_ops ext4_iomap_ops = { +const struct iomap_ops ext4_iomap_ops = { .iomap_begin = ext4_iomap_begin, .iomap_end = ext4_iomap_end, }; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index a2d45db32cd5..ec0848fcca02 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -658,9 +658,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, struct kmem_cache *cachep; int ret, tries = 0; + rcu_read_lock(); gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); if (gl && !lockref_get_not_dead(&gl->gl_lockref)) gl = NULL; + rcu_read_unlock(); *glp = gl; if (gl) @@ -728,15 +730,18 @@ again: if (ret == -EEXIST) { ret = 0; + rcu_read_lock(); tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) { if (++tries < 100) { + rcu_read_unlock(); cond_resched(); goto again; } tmp = NULL; ret = -ENOMEM; } + rcu_read_unlock(); } else { WARN_ON_ONCE(ret); } @@ -1420,26 +1425,32 @@ static struct shrinker glock_shrinker = { * @sdp: the filesystem * @bucket: the bucket * + * Note that the function can be called multiple times on the same + * object. So the user must ensure that the function can cope with + * that. */ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) { struct gfs2_glock *gl; - struct rhash_head *pos; - const struct bucket_table *tbl; - int i; + struct rhashtable_iter iter; - rcu_read_lock(); - tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table); - for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) { + rhashtable_walk_enter(&gl_hash_table, &iter); + + do { + gl = ERR_PTR(rhashtable_walk_start(&iter)); + if (gl) + continue; + + while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl)) if ((gl->gl_name.ln_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref)) examiner(gl); - } - } - rcu_read_unlock(); - cond_resched(); + + rhashtable_walk_stop(&iter); + } while (cond_resched(), gl == ERR_PTR(-EAGAIN)); + + rhashtable_walk_exit(&iter); } /** diff --git a/fs/internal.h b/fs/internal.h index b63cf3af2dc2..11c6d89dce9c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -182,7 +182,7 @@ typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, void *data, struct iomap *iomap); loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap_ops *ops, void *data, + unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor); /* direct-io.c: */ diff --git a/fs/iomap.c b/fs/iomap.c index a51cb4c07d4d..d89f70bbb952 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -41,7 +41,7 @@ */ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, - struct iomap_ops *ops, void *data, iomap_actor_t actor) + const struct iomap_ops *ops, void *data, iomap_actor_t actor) { struct iomap iomap = { 0 }; loff_t written = 0, ret; @@ -235,7 +235,7 @@ again: ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter, - struct iomap_ops *ops) + const struct iomap_ops *ops) { struct inode *inode = iocb->ki_filp->f_mapping->host; loff_t pos = iocb->ki_pos, ret = 0, written = 0; @@ -318,7 +318,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, - struct iomap_ops *ops) + const struct iomap_ops *ops) { loff_t ret; @@ -398,7 +398,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, - struct iomap_ops *ops) + const struct iomap_ops *ops) { loff_t ret; @@ -418,7 +418,7 @@ EXPORT_SYMBOL_GPL(iomap_zero_range); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - struct iomap_ops *ops) + const struct iomap_ops *ops) { unsigned blocksize = (1 << inode->i_blkbits); unsigned off = pos & (blocksize - 1); @@ -446,7 +446,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, } int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - struct iomap_ops *ops) + const struct iomap_ops *ops) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); @@ -545,7 +545,7 @@ iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, - loff_t start, loff_t len, struct iomap_ops *ops) + loff_t start, loff_t len, const struct iomap_ops *ops) { struct fiemap_ctx ctx; loff_t ret; @@ -839,8 +839,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, } ssize_t -iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops, - iomap_dio_end_io_t end_io) +iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + const struct iomap_ops *ops, iomap_dio_end_io_t end_io) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index cf4c636ff4da..439b946c4808 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -41,6 +41,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn) static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) { + if (!kn) + return strlcpy(buf, "(null)", buflen); + return strlcpy(buf, kn->parent ? kn->name : "/", buflen); } @@ -110,6 +113,8 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, * kn_to: /n1/n2/n3 [depth=3] * result: /../.. * + * [3] when @kn_to is NULL result will be "(null)" + * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. @@ -123,6 +128,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, size_t depth_from, depth_to, len = 0; int i, j; + if (!kn_to) + return strlcpy(buf, "(null)", buflen); + if (!kn_from) kn_from = kernfs_root(kn_to)->kn; @@ -166,6 +174,8 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, * similar to strlcpy(). It returns the length of @kn's name and if @buf * isn't long enough, it's filled upto @buflen-1 and nul terminated. * + * Fills buffer with "(null)" if @kn is NULL. + * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) diff --git a/fs/mount.h b/fs/mount.h index 2c856fc47ae3..2826543a131d 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -89,7 +89,6 @@ static inline int is_mounted(struct vfsmount *mnt) } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); -extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); extern bool legitimize_mnt(struct vfsmount *, unsigned); diff --git a/fs/namei.c b/fs/namei.c index ad74877e1442..da689c9c005e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1100,7 +1100,6 @@ static int follow_automount(struct path *path, struct nameidata *nd, bool *need_mntput) { struct vfsmount *mnt; - const struct cred *old_cred; int err; if (!path->dentry->d_op || !path->dentry->d_op->d_automount) @@ -1129,9 +1128,7 @@ static int follow_automount(struct path *path, struct nameidata *nd, if (nd->total_link_count >= 40) return -ELOOP; - old_cred = override_creds(&init_cred); mnt = path->dentry->d_op->d_automount(path); - revert_creds(old_cred); if (IS_ERR(mnt)) { /* * The filesystem is allowed to return -EISDIR here to indicate @@ -2941,10 +2938,16 @@ static inline int open_to_namei_flags(int flag) static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { + struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; + s_user_ns = dir->dentry->d_sb->s_user_ns; + if (!kuid_has_mapping(s_user_ns, current_fsuid()) || + !kgid_has_mapping(s_user_ns, current_fsgid())) + return -EOVERFLOW; + error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; diff --git a/fs/namespace.c b/fs/namespace.c index 487ba30bb5c6..8bfad42c1ccf 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -637,28 +637,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) } /* - * find the last mount at @dentry on vfsmount @mnt. - * mount_lock must be held. - */ -struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) -{ - struct mount *p, *res = NULL; - p = __lookup_mnt(mnt, dentry); - if (!p) - goto out; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - hlist_for_each_entry_continue(p, mnt_hash) { - if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) - break; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - } -out: - return res; -} - -/* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the @@ -878,6 +856,13 @@ void mnt_set_mountpoint(struct mount *mnt, hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } +static void __attach_mnt(struct mount *mnt, struct mount *parent) +{ + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); +} + /* * vfsmount lock must be held for write */ @@ -886,28 +871,45 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + __attach_mnt(mnt, parent); } -static void attach_shadowed(struct mount *mnt, - struct mount *parent, - struct mount *shadows) +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { - if (shadows) { - hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash); - list_add(&mnt->mnt_child, &shadows->mnt_child); - } else { - hlist_add_head_rcu(&mnt->mnt_hash, - m_hash(&parent->mnt, mnt->mnt_mountpoint)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); - } + struct mountpoint *old_mp = mnt->mnt_mp; + struct dentry *old_mountpoint = mnt->mnt_mountpoint; + struct mount *old_parent = mnt->mnt_parent; + + list_del_init(&mnt->mnt_child); + hlist_del_init(&mnt->mnt_mp_list); + hlist_del_init_rcu(&mnt->mnt_hash); + + attach_mnt(mnt, parent, mp); + + put_mountpoint(old_mp); + + /* + * Safely avoid even the suggestion this code might sleep or + * lock the mount hash by taking advantage of the knowledge that + * mnt_change_mountpoint will not release the final reference + * to a mountpoint. + * + * During mounting, the mount passed in as the parent mount will + * continue to use the old mountpoint and during unmounting, the + * old mountpoint will continue to exist until namespace_unlock, + * which happens well after mnt_change_mountpoint. + */ + spin_lock(&old_mountpoint->d_lock); + old_mountpoint->d_lockref.count--; + spin_unlock(&old_mountpoint->d_lock); + + mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ -static void commit_tree(struct mount *mnt, struct mount *shadows) +static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; @@ -925,7 +927,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) n->mounts += n->pending_mounts; n->pending_mounts = 0; - attach_shadowed(mnt, parent, shadows); + __attach_mnt(mnt, parent); touch_mnt_namespace(n); } @@ -989,6 +991,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void } EXPORT_SYMBOL_GPL(vfs_kern_mount); +struct vfsmount * +vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, + const char *name, void *data) +{ + /* Until it is worked out how to pass the user namespace + * through from the parent mount to the submount don't support + * unprivileged mounts with submounts. + */ + if (mountpoint->d_sb->s_user_ns != &init_user_ns) + return ERR_PTR(-EPERM); + + return vfs_kern_mount(type, MS_SUBMOUNT, name, data); +} +EXPORT_SYMBOL_GPL(vfs_submount); + static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { @@ -1764,7 +1781,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { - struct mount *t = NULL; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { s = skip_mnt_tree(s); @@ -1786,14 +1802,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - mnt_set_mountpoint(parent, p->mnt_mp, q); - if (!list_empty(&parent->mnt_mounts)) { - t = list_last_entry(&parent->mnt_mounts, - struct mount, mnt_child); - if (t->mnt_mp != p->mnt_mp) - t = NULL; - } - attach_shadowed(q, parent, t); + attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } @@ -1992,10 +2001,18 @@ static int attach_recursive_mnt(struct mount *source_mnt, { HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; + struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; + /* Preallocate a mountpoint in case the new mounts need + * to be tucked under other mounts. + */ + smp = get_mountpoint(source_mnt->mnt.mnt_root); + if (IS_ERR(smp)) + return PTR_ERR(smp); + /* Is there space to add these mounts to the mount namespace? */ if (!parent_path) { err = count_mounts(ns, source_mnt); @@ -2022,16 +2039,19 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); - commit_tree(source_mnt, NULL); + commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); - q = __lookup_mnt_last(&child->mnt_parent->mnt, - child->mnt_mountpoint); - commit_tree(child, q); + q = __lookup_mnt(&child->mnt_parent->mnt, + child->mnt_mountpoint); + if (q) + mnt_change_mountpoint(child, smp, q); + commit_tree(child); } + put_mountpoint(smp); unlock_mount_hash(); return 0; @@ -2046,6 +2066,11 @@ static int attach_recursive_mnt(struct mount *source_mnt, cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; + + read_seqlock_excl(&mount_lock); + put_mountpoint(smp); + read_sequnlock_excl(&mount_lock); + return err; } @@ -2794,7 +2819,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | - MS_STRICTATIME | MS_NOREMOTELOCK); + MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT); if (flags & MS_REMOUNT) retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 5551e8ef67fd..e49d831c4e85 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -226,7 +226,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, const char *devname, struct nfs_clone_mount *mountdata) { - return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata); + return vfs_submount(mountdata->dentry, &nfs_xdev_fs_type, devname, mountdata); } /** diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index d21104912676..d8b040bd9814 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -279,7 +279,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, mountdata->hostname, mountdata->mnt_path); - mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata); + mnt = vfs_submount(mountdata->dentry, &nfs4_referral_fs_type, page, mountdata); if (!IS_ERR(mnt)) break; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index b00d53d13d47..006068526542 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -728,8 +728,6 @@ static void nfs_inode_remove_request(struct nfs_page *req) if (likely(head->wb_page && !PageSwapCache(head->wb_page))) { set_page_private(head->wb_page, 0); ClearPagePrivate(head->wb_page); - smp_mb__after_atomic(); - wake_up_page(head->wb_page, PG_private); clear_bit(PG_MAPPED, &head->wb_flags); } nfsi->nrequests--; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 1fc07a9c70e9..e122da696f1b 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -614,6 +614,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) { struct nfs4_client *clp = ls->ls_stid.sc_client; char addr_str[INET6_ADDRSTRLEN]; + static char const nfsd_recall_failed[] = "/sbin/nfsd-recall-failed"; static char *envp[] = { "HOME=/", "TERM=linux", @@ -629,12 +630,13 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) "nfsd: client %s failed to respond to layout recall. " " Fencing..\n", addr_str); - argv[0] = "/sbin/nfsd-recall-failed"; + argv[0] = (char *)nfsd_recall_failed; argv[1] = addr_str; argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id; argv[3] = NULL; - error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + error = call_usermodehelper(nfsd_recall_failed, argv, envp, + UMH_WAIT_PROC); if (error) { printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n", addr_str, error); diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index a6f5907a3fee..7c461fd49c4c 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -30,3 +30,20 @@ extern int inotify_handle_event(struct fsnotify_group *group, const unsigned char *file_name, u32 cookie); extern const struct fsnotify_ops inotify_fsnotify_ops; + +#ifdef CONFIG_INOTIFY_USER +static inline void dec_inotify_instances(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES); +} + +static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts) +{ + return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES); +} + +static inline void dec_inotify_watches(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES); +} +#endif diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 19e7ec109a75..f36c29398de3 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -165,10 +165,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group) /* ideally the idr is empty and we won't hit the BUG in the callback */ idr_for_each(&group->inotify_data.idr, idr_callback, group); idr_destroy(&group->inotify_data.idr); - if (group->inotify_data.user) { - atomic_dec(&group->inotify_data.user->inotify_devs); - free_uid(group->inotify_data.user); - } + if (group->inotify_data.ucounts) + dec_inotify_instances(group->inotify_data.ucounts); } static void inotify_free_event(struct fsnotify_event *fsn_event) diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 69d1ea3d292a..1cf41c623be1 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -44,10 +44,8 @@ #include <asm/ioctls.h> -/* these are configurable via /proc/sys/fs/inotify/ */ -static int inotify_max_user_instances __read_mostly; +/* configurable via /proc/sys/fs/inotify/ */ static int inotify_max_queued_events __read_mostly; -static int inotify_max_user_watches __read_mostly; static struct kmem_cache *inotify_inode_mark_cachep __read_mostly; @@ -60,7 +58,7 @@ static int zero; struct ctl_table inotify_table[] = { { .procname = "max_user_instances", - .data = &inotify_max_user_instances, + .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -68,7 +66,7 @@ struct ctl_table inotify_table[] = { }, { .procname = "max_user_watches", - .data = &inotify_max_user_watches, + .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES], .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -500,7 +498,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, /* remove this mark from the idr */ inotify_remove_from_idr(group, i_mark); - atomic_dec(&group->inotify_data.user->inotify_watches); + dec_inotify_watches(group->inotify_data.ucounts); } /* ding dong the mark is dead */ @@ -584,14 +582,17 @@ static int inotify_new_watch(struct fsnotify_group *group, tmp_i_mark->fsn_mark.mask = mask; tmp_i_mark->wd = -1; - ret = -ENOSPC; - if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches) - goto out_err; - ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark); if (ret) goto out_err; + /* increment the number of watches the user has */ + if (!inc_inotify_watches(group->inotify_data.ucounts)) { + inotify_remove_from_idr(group, tmp_i_mark); + ret = -ENOSPC; + goto out_err; + } + /* we are on the idr, now get on the inode */ ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode, NULL, 0); @@ -601,8 +602,6 @@ static int inotify_new_watch(struct fsnotify_group *group, goto out_err; } - /* increment the number of watches the user has */ - atomic_inc(&group->inotify_data.user->inotify_watches); /* return the watch descriptor for this new mark */ ret = tmp_i_mark->wd; @@ -653,10 +652,11 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) spin_lock_init(&group->inotify_data.idr_lock); idr_init(&group->inotify_data.idr); - group->inotify_data.user = get_current_user(); + group->inotify_data.ucounts = inc_ucount(current_user_ns(), + current_euid(), + UCOUNT_INOTIFY_INSTANCES); - if (atomic_inc_return(&group->inotify_data.user->inotify_devs) > - inotify_max_user_instances) { + if (!group->inotify_data.ucounts) { fsnotify_destroy_group(group); return ERR_PTR(-EMFILE); } @@ -819,8 +819,8 @@ static int __init inotify_user_setup(void) inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC); inotify_max_queued_events = 16384; - inotify_max_user_instances = 128; - inotify_max_user_watches = 8192; + init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128; + init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192; return 0; } diff --git a/fs/nsfs.c b/fs/nsfs.c index 8c9fb29c6673..1656843e87d2 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -7,6 +7,7 @@ #include <linux/seq_file.h> #include <linux/user_namespace.h> #include <linux/nsfs.h> +#include <linux/uaccess.h> static struct vfsmount *nsfs_mnt; @@ -163,7 +164,10 @@ int open_related_ns(struct ns_common *ns, static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { + struct user_namespace *user_ns; struct ns_common *ns = get_proc_ns(file_inode(filp)); + uid_t __user *argp; + uid_t uid; switch (ioctl) { case NS_GET_USERNS: @@ -172,6 +176,15 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (!ns->ops->get_parent) return -EINVAL; return open_related_ns(ns, ns->ops->get_parent); + case NS_GET_NSTYPE: + return ns->ops->type; + case NS_GET_OWNER_UID: + if (ns->ops->type != CLONE_NEWUSER) + return -EINVAL; + user_ns = container_of(ns, struct user_namespace, ns); + argp = (uid_t __user *) arg; + uid = from_kuid_munged(current_user_ns(), user_ns->owner); + return put_user(uid, argp); default: return -ENOTTY; } diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index bed1fcb63088..dc22ba8c710f 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -283,16 +283,14 @@ int ocfs2_set_acl(handle_t *handle, int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct buffer_head *bh = NULL; - int status = 0; + int status, had_lock; + struct ocfs2_lock_holder oh; - status = ocfs2_inode_lock(inode, &bh, 1); - if (status < 0) { - if (status != -ENOENT) - mlog_errno(status); - return status; - } + had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh); + if (had_lock < 0) + return had_lock; status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL); - ocfs2_inode_unlock(inode, 1); + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); brelse(bh); return status; } @@ -302,21 +300,20 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) struct ocfs2_super *osb; struct buffer_head *di_bh = NULL; struct posix_acl *acl; - int ret; + int had_lock; + struct ocfs2_lock_holder oh; osb = OCFS2_SB(inode->i_sb); if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) return NULL; - ret = ocfs2_inode_lock(inode, &di_bh, 0); - if (ret < 0) { - if (ret != -ENOENT) - mlog_errno(ret); - return ERR_PTR(ret); - } + + had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh); + if (had_lock < 0) + return ERR_PTR(had_lock); acl = ocfs2_get_acl_nolock(inode, type, di_bh); - ocfs2_inode_unlock(inode, 0); + ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); brelse(di_bh); return acl; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 77d1632e905d..8dce4099a6ca 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -532,6 +532,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res) init_waitqueue_head(&res->l_event); INIT_LIST_HEAD(&res->l_blocked_list); INIT_LIST_HEAD(&res->l_mask_waiters); + INIT_LIST_HEAD(&res->l_holders); } void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res, @@ -749,6 +750,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res) res->l_flags = 0UL; } +/* + * Keep a list of processes who have interest in a lockres. + * Note: this is now only uesed for check recursive cluster locking. + */ +static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + INIT_LIST_HEAD(&oh->oh_list); + oh->oh_owner_pid = get_pid(task_pid(current)); + + spin_lock(&lockres->l_lock); + list_add_tail(&oh->oh_list, &lockres->l_holders); + spin_unlock(&lockres->l_lock); +} + +static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + spin_lock(&lockres->l_lock); + list_del(&oh->oh_list); + spin_unlock(&lockres->l_lock); + + put_pid(oh->oh_owner_pid); +} + +static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres) +{ + struct ocfs2_lock_holder *oh; + struct pid *pid; + + /* look in the list of holders for one with the current task as owner */ + spin_lock(&lockres->l_lock); + pid = task_pid(current); + list_for_each_entry(oh, &lockres->l_holders, oh_list) { + if (oh->oh_owner_pid == pid) { + spin_unlock(&lockres->l_lock); + return 1; + } + } + spin_unlock(&lockres->l_lock); + + return 0; +} + static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres, int level) { @@ -2333,8 +2378,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, goto getbh; } - if (ocfs2_mount_local(osb)) - goto local; + if ((arg_flags & OCFS2_META_LOCK_GETBH) || + ocfs2_mount_local(osb)) + goto update; if (!(arg_flags & OCFS2_META_LOCK_RECOVERY)) ocfs2_wait_for_recovery(osb); @@ -2363,7 +2409,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, if (!(arg_flags & OCFS2_META_LOCK_RECOVERY)) ocfs2_wait_for_recovery(osb); -local: +update: /* * We only see this flag if we're being called from * ocfs2_read_locked_inode(). It means we're locking an inode @@ -2497,6 +2543,59 @@ void ocfs2_inode_unlock(struct inode *inode, ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); } +/* + * This _tracker variantes are introduced to deal with the recursive cluster + * locking issue. The idea is to keep track of a lock holder on the stack of + * the current process. If there's a lock holder on the stack, we know the + * task context is already protected by cluster locking. Currently, they're + * used in some VFS entry routines. + * + * return < 0 on error, return == 0 if there's no lock holder on the stack + * before this call, return == 1 if this call would be a recursive locking. + */ +int ocfs2_inode_lock_tracker(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + struct ocfs2_lock_holder *oh) +{ + int status; + int arg_flags = 0, has_locked; + struct ocfs2_lock_res *lockres; + + lockres = &OCFS2_I(inode)->ip_inode_lockres; + has_locked = ocfs2_is_locked_by_me(lockres); + /* Just get buffer head if the cluster lock has been taken */ + if (has_locked) + arg_flags = OCFS2_META_LOCK_GETBH; + + if (likely(!has_locked || ret_bh)) { + status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags); + if (status < 0) { + if (status != -ENOENT) + mlog_errno(status); + return status; + } + } + if (!has_locked) + ocfs2_add_holder(lockres, oh); + + return has_locked; +} + +void ocfs2_inode_unlock_tracker(struct inode *inode, + int ex, + struct ocfs2_lock_holder *oh, + int had_lock) +{ + struct ocfs2_lock_res *lockres; + + lockres = &OCFS2_I(inode)->ip_inode_lockres; + if (!had_lock) { + ocfs2_remove_holder(lockres, oh); + ocfs2_inode_unlock(inode, ex); + } +} + int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno) { struct ocfs2_lock_res *lockres; diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index d293a22c32c5..a7fc18ba0dc1 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb { __be32 lvb_os_seqno; }; +struct ocfs2_lock_holder { + struct list_head oh_list; + struct pid *oh_owner_pid; +}; + /* ocfs2_inode_lock_full() 'arg_flags' flags */ /* don't wait on recovery. */ #define OCFS2_META_LOCK_RECOVERY (0x01) @@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb { #define OCFS2_META_LOCK_NOQUEUE (0x02) /* don't block waiting for the downconvert thread, instead return -EAGAIN */ #define OCFS2_LOCK_NONBLOCK (0x04) +/* just get back disk inode bh if we've got cluster lock. */ +#define OCFS2_META_LOCK_GETBH (0x08) /* Locking subclasses of inode cluster lock */ enum { @@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug); /* To set the locking protocol on module initialization */ void ocfs2_set_locking_protocol(void); + +/* The _tracker pair is used to avoid cluster recursive locking */ +int ocfs2_inode_lock_tracker(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + struct ocfs2_lock_holder *oh); +void ocfs2_inode_unlock_tracker(struct inode *inode, + int ex, + struct ocfs2_lock_holder *oh, + int had_lock); + #endif /* DLMGLUE_H */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index c4889655d32b..7b6a146327d7 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1138,6 +1138,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) handle_t *handle = NULL; struct dquot *transfer_to[MAXQUOTAS] = { }; int qtype; + int had_lock; + struct ocfs2_lock_holder oh; trace_ocfs2_setattr(inode, dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -1173,11 +1175,30 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) } } - status = ocfs2_inode_lock(inode, &bh, 1); - if (status < 0) { - if (status != -ENOENT) - mlog_errno(status); + had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh); + if (had_lock < 0) { + status = had_lock; goto bail_unlock_rw; + } else if (had_lock) { + /* + * As far as we know, ocfs2_setattr() could only be the first + * VFS entry point in the call chain of recursive cluster + * locking issue. + * + * For instance: + * chmod_common() + * notify_change() + * ocfs2_setattr() + * posix_acl_chmod() + * ocfs2_iop_get_acl() + * + * But, we're not 100% sure if it's always true, because the + * ordering of the VFS entry points in the call chain is out + * of our control. So, we'd better dump the stack here to + * catch the other cases of recursive locking. + */ + mlog(ML_ERROR, "Another case of recursive locking:\n"); + dump_stack(); } inode_locked = 1; @@ -1260,8 +1281,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) bail_commit: ocfs2_commit_trans(osb, handle); bail_unlock: - if (status) { - ocfs2_inode_unlock(inode, 1); + if (status && inode_locked) { + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); inode_locked = 0; } bail_unlock_rw: @@ -1279,7 +1300,7 @@ bail: mlog_errno(status); } if (inode_locked) - ocfs2_inode_unlock(inode, 1); + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); brelse(bh); return status; @@ -1320,21 +1341,32 @@ bail: int ocfs2_permission(struct inode *inode, int mask) { - int ret; + int ret, had_lock; + struct ocfs2_lock_holder oh; if (mask & MAY_NOT_BLOCK) return -ECHILD; - ret = ocfs2_inode_lock(inode, NULL, 0); - if (ret) { - if (ret != -ENOENT) - mlog_errno(ret); + had_lock = ocfs2_inode_lock_tracker(inode, NULL, 0, &oh); + if (had_lock < 0) { + ret = had_lock; goto out; + } else if (had_lock) { + /* See comments in ocfs2_setattr() for details. + * The call chain of this case could be: + * do_sys_open() + * may_open() + * inode_permission() + * ocfs2_permission() + * ocfs2_iop_get_acl() + */ + mlog(ML_ERROR, "Another case of recursive locking:\n"); + dump_stack(); } ret = generic_permission(inode, mask); - ocfs2_inode_unlock(inode, 0); + ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); out: return ret; } diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 7e5958b0be6b..0c39d71c67a1 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -172,6 +172,7 @@ struct ocfs2_lock_res { struct list_head l_blocked_list; struct list_head l_mask_waiters; + struct list_head l_holders; unsigned long l_flags; char l_name[OCFS2_LOCK_ID_MAX_LEN]; diff --git a/fs/pnode.c b/fs/pnode.c index 06a793f4ae38..5bc7896d122a 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -322,6 +322,21 @@ out: return ret; } +static struct mount *find_topper(struct mount *mnt) +{ + /* If there is exactly one mount covering mnt completely return it. */ + struct mount *child; + + if (!list_is_singular(&mnt->mnt_mounts)) + return NULL; + + child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child); + if (child->mnt_mountpoint != mnt->mnt.mnt_root) + return NULL; + + return child; +} + /* * return true if the refcount is greater than count */ @@ -342,9 +357,8 @@ static inline int do_refcount_check(struct mount *mnt, int count) */ int propagate_mount_busy(struct mount *mnt, int refcnt) { - struct mount *m, *child; + struct mount *m, *child, *topper; struct mount *parent = mnt->mnt_parent; - int ret = 0; if (mnt == parent) return do_refcount_check(mnt, refcnt); @@ -359,12 +373,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); - if (child && list_empty(&child->mnt_mounts) && - (ret = do_refcount_check(child, 1))) - break; + int count = 1; + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); + if (!child) + continue; + + /* Is there exactly one mount on the child that covers + * it completely whose reference should be ignored? + */ + topper = find_topper(child); + if (topper) + count += 1; + else if (!list_empty(&child->mnt_mounts)) + continue; + + if (do_refcount_check(child, count)) + return 1; } - return ret; + return 0; } /* @@ -381,7 +407,7 @@ void propagate_mount_unlock(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (child) child->mnt.mnt_flags &= ~MNT_LOCKED; } @@ -399,9 +425,11 @@ static void mark_umount_candidates(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt_last(&m->mnt, + struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); - if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) { + if (!child || (child->mnt.mnt_flags & MNT_UMOUNT)) + continue; + if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) { SET_MNT_MARK(child); } } @@ -420,8 +448,8 @@ static void __propagate_umount(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - - struct mount *child = __lookup_mnt_last(&m->mnt, + struct mount *topper; + struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); /* * umount the child only if the child has no children @@ -430,6 +458,15 @@ static void __propagate_umount(struct mount *mnt) if (!child || !IS_MNT_MARKED(child)) continue; CLEAR_MNT_MARK(child); + + /* If there is exactly one mount covering all of child + * replace child with that mount. + */ + topper = find_topper(child); + if (topper) + mnt_change_mountpoint(child->mnt_parent, child->mnt_mp, + topper); + if (list_empty(&child->mnt_mounts)) { list_del_init(&child->mnt_child); child->mnt.mnt_flags |= MNT_UMOUNT; diff --git a/fs/pnode.h b/fs/pnode.h index 550f5a8b4fcf..dc87e65becd2 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root); unsigned int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, + struct mount *mnt); struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); diff --git a/fs/proc/base.c b/fs/proc/base.c index b1f7d30e96c2..b73b4de8fb36 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1667,12 +1667,63 @@ const struct inode_operations proc_pid_link_inode_operations = { /* building an inode */ +void task_dump_owner(struct task_struct *task, mode_t mode, + kuid_t *ruid, kgid_t *rgid) +{ + /* Depending on the state of dumpable compute who should own a + * proc file for a task. + */ + const struct cred *cred; + kuid_t uid; + kgid_t gid; + + /* Default to the tasks effective ownership */ + rcu_read_lock(); + cred = __task_cred(task); + uid = cred->euid; + gid = cred->egid; + rcu_read_unlock(); + + /* + * Before the /proc/pid/status file was created the only way to read + * the effective uid of a /process was to stat /proc/pid. Reading + * /proc/pid/status is slow enough that procps and other packages + * kept stating /proc/pid. To keep the rules in /proc simple I have + * made this apply to all per process world readable and executable + * directories. + */ + if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) { + struct mm_struct *mm; + task_lock(task); + mm = task->mm; + /* Make non-dumpable tasks owned by some root */ + if (mm) { + if (get_dumpable(mm) != SUID_DUMP_USER) { + struct user_namespace *user_ns = mm->user_ns; + + uid = make_kuid(user_ns, 0); + if (!uid_valid(uid)) + uid = GLOBAL_ROOT_UID; + + gid = make_kgid(user_ns, 0); + if (!gid_valid(gid)) + gid = GLOBAL_ROOT_GID; + } + } else { + uid = GLOBAL_ROOT_UID; + gid = GLOBAL_ROOT_GID; + } + task_unlock(task); + } + *ruid = uid; + *rgid = gid; +} + struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; - const struct cred *cred; /* We need a new inode */ @@ -1694,13 +1745,7 @@ struct inode *proc_pid_make_inode(struct super_block * sb, if (!ei->pid) goto out_unlock; - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); out: @@ -1715,7 +1760,6 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = d_inode(dentry); struct task_struct *task; - const struct cred *cred; struct pid_namespace *pid = dentry->d_sb->s_fs_info; generic_fillattr(inode, stat); @@ -1733,12 +1777,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) */ return -ENOENT; } - if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || - task_dumpable(task)) { - cred = __task_cred(task); - stat->uid = cred->euid; - stat->gid = cred->egid; - } + task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid); } rcu_read_unlock(); return 0; @@ -1754,18 +1793,11 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * - * Before the /proc/pid/status file was created the only way to read - * the effective uid of a /process was to stat /proc/pid. Reading - * /proc/pid/status is slow enough that procps and other packages - * kept stating /proc/pid. To keep the rules in /proc simple I have - * made this apply to all per process world readable and executable - * directories. */ int pid_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; - const struct cred *cred; if (flags & LOOKUP_RCU) return -ECHILD; @@ -1774,17 +1806,8 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags) task = get_proc_task(inode); if (task) { - if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || - task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); + inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); put_task_struct(task); @@ -1881,7 +1904,6 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) bool exact_vma_exists = false; struct mm_struct *mm = NULL; struct task_struct *task; - const struct cred *cred; struct inode *inode; int status = 0; @@ -1906,16 +1928,8 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) mmput(mm); if (exact_vma_exists) { - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); + security_task_to_inode(task, inode); status = 1; } @@ -2488,6 +2502,12 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, length = -ESRCH; if (!task) goto out_no_task; + + /* A task may only write its own attributes. */ + length = -EACCES; + if (current != task) + goto out; + if (count > PAGE_SIZE) count = PAGE_SIZE; @@ -2503,14 +2523,13 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, } /* Guard against adverse ptrace interaction */ - length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + length = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); if (length < 0) goto out_free; - length = security_setprocattr(task, - (char*)file->f_path.dentry->d_name.name, + length = security_setprocattr(file->f_path.dentry->d_name.name, page, count); - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); out: diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 4274f83bf100..00ce1531b2f5 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -84,7 +84,6 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) { struct files_struct *files; struct task_struct *task; - const struct cred *cred; struct inode *inode; unsigned int fd; @@ -108,16 +107,7 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) rcu_read_unlock(); put_files_struct(files); - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); if (S_ISLNK(inode->i_mode)) { unsigned i_mode = S_IFLNK; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 842a5ff5b85c..7ad9ed7958af 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -43,10 +43,11 @@ static void proc_evict_inode(struct inode *inode) de = PDE(inode); if (de) pde_put(de); + head = PROC_I(inode)->sysctl; if (head) { RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL); - sysctl_head_put(head); + proc_sys_evict_inode(inode, head); } } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 2de5194ba378..5d6960f5f1c0 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -65,6 +65,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; + struct list_head sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; }; @@ -97,20 +98,8 @@ static inline struct task_struct *get_proc_task(struct inode *inode) return get_pid_task(proc_pid(inode), PIDTYPE_PID); } -static inline int task_dumpable(struct task_struct *task) -{ - int dumpable = 0; - struct mm_struct *mm; - - task_lock(task); - mm = task->mm; - if (mm) - dumpable = get_dumpable(mm); - task_unlock(task); - if (dumpable == SUID_DUMP_USER) - return 1; - return 0; -} +void task_dump_owner(struct task_struct *task, mode_t mode, + kuid_t *ruid, kgid_t *rgid); static inline unsigned name_to_int(const struct qstr *qstr) { @@ -249,10 +238,12 @@ extern void proc_thread_self_init(void); */ #ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); -extern void sysctl_head_put(struct ctl_table_header *); +extern void proc_sys_evict_inode(struct inode *inode, + struct ctl_table_header *head); #else static inline void proc_sys_init(void) { } -static inline void sysctl_head_put(struct ctl_table_header *head) { } +static inline void proc_sys_evict_inode(struct inode *inode, + struct ctl_table_header *head) { } #endif /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d4e37acd4821..3e64c6502dc8 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -190,6 +190,7 @@ static void init_header(struct ctl_table_header *head, head->set = set; head->parent = NULL; head->node = node; + INIT_LIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; for (entry = table; entry->procname; entry++, node++) @@ -259,6 +260,27 @@ static void unuse_table(struct ctl_table_header *p) complete(p->unregistering); } +/* called under sysctl_lock */ +static void proc_sys_prune_dcache(struct ctl_table_header *head) +{ + struct inode *inode, *prev = NULL; + struct proc_inode *ei; + + rcu_read_lock(); + list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) { + inode = igrab(&ei->vfs_inode); + if (inode) { + rcu_read_unlock(); + iput(prev); + prev = inode; + d_prune_aliases(inode); + rcu_read_lock(); + } + } + rcu_read_unlock(); + iput(prev); +} + /* called under sysctl_lock, will reacquire if has to wait */ static void start_unregistering(struct ctl_table_header *p) { @@ -272,31 +294,22 @@ static void start_unregistering(struct ctl_table_header *p) p->unregistering = &wait; spin_unlock(&sysctl_lock); wait_for_completion(&wait); - spin_lock(&sysctl_lock); } else { /* anything non-NULL; we'll never dereference it */ p->unregistering = ERR_PTR(-EINVAL); + spin_unlock(&sysctl_lock); } /* + * Prune dentries for unregistered sysctls: namespaced sysctls + * can have duplicate names and contaminate dcache very badly. + */ + proc_sys_prune_dcache(p); + /* * do not remove from the list until nobody holds it; walking the * list in do_sysctl() relies on that. */ - erase_header(p); -} - -static void sysctl_head_get(struct ctl_table_header *head) -{ spin_lock(&sysctl_lock); - head->count++; - spin_unlock(&sysctl_lock); -} - -void sysctl_head_put(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - if (!--head->count) - kfree_rcu(head, rcu); - spin_unlock(&sysctl_lock); + erase_header(p); } static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) @@ -440,10 +453,20 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode->i_ino = get_next_ino(); - sysctl_head_get(head); ei = PROC_I(inode); + + spin_lock(&sysctl_lock); + if (unlikely(head->unregistering)) { + spin_unlock(&sysctl_lock); + iput(inode); + inode = NULL; + goto out; + } ei->sysctl = head; ei->sysctl_entry = table; + list_add_rcu(&ei->sysctl_inodes, &head->inodes); + head->count++; + spin_unlock(&sysctl_lock); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mode = table->mode; @@ -466,6 +489,15 @@ out: return inode; } +void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + list_del_rcu(&PROC_I(inode)->sysctl_inodes); + if (!--head->count) + kfree_rcu(head, rcu); + spin_unlock(&sysctl_lock); +} + static struct ctl_table_header *grab_header(struct inode *inode) { struct ctl_table_header *head = PROC_I(inode)->sysctl; diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 1d887efaaf71..11f918d34b1e 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -133,7 +133,8 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, struct persistent_ram_zone *prz; int i = (*c)++; - if (i >= max) + /* Give up if we never existed or have hit the end. */ + if (!przs || i >= max) return NULL; prz = przs[i]; @@ -280,7 +281,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, 1, id, type, PSTORE_TYPE_PMSG, 0); /* ftrace is last since it may want to dynamically allocate memory. */ - if (!prz_ok(prz) && cxt->fprzs) { + if (!prz_ok(prz)) { if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) { prz = ramoops_get_next_prz(cxt->fprzs, &cxt->ftrace_read_cnt, 1, id, type, diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index a857338b7dab..bc927e30bdcc 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -467,8 +467,7 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, } static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, - struct persistent_ram_ecc_info *ecc_info, - unsigned long flags) + struct persistent_ram_ecc_info *ecc_info) { int ret; @@ -494,10 +493,9 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, prz->buffer->sig); } + /* Rewind missing or invalid memory area. */ prz->buffer->sig = sig; persistent_ram_zap(prz); - prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock); - prz->flags = flags; return 0; } @@ -533,11 +531,15 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } + /* Initialize general buffer state. */ + prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock); + prz->flags = flags; + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; - ret = persistent_ram_post_init(prz, sig, ecc_info, flags); + ret = persistent_ram_post_init(prz, sig, ecc_info); if (ret) goto err; diff --git a/fs/super.c b/fs/super.c index ea662b0e5e78..b8b6a086c03b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -469,7 +469,7 @@ struct super_block *sget_userns(struct file_system_type *type, struct super_block *old; int err; - if (!(flags & MS_KERNMOUNT) && + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !(type->fs_flags & FS_USERNS_MOUNT) && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -499,7 +499,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type, flags, user_ns); + s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -540,8 +540,15 @@ struct super_block *sget(struct file_system_type *type, { struct user_namespace *user_ns = current_user_ns(); + /* We don't yet pass the user namespace of the parent + * mount through to here so always use &init_user_ns + * until that changes. + */ + if (flags & MS_SUBMOUNT) + user_ns = &init_user_ns; + /* Ensure the requestor has permissions over the target filesystem */ - if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN)) + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); return sget_userns(type, test, set, flags, user_ns, data); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 43953e03c356..18406158e13f 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -12,6 +12,7 @@ * mm/ksm.c (mm hashing). */ +#include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched.h> #include <linux/mm.h> @@ -26,6 +27,7 @@ #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> +#include <linux/hugetlb.h> static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; @@ -45,12 +47,16 @@ struct userfaultfd_ctx { wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; + /* waitqueue head for events */ + wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ struct seqcount refile_seq; /* pseudo fd refcounting */ atomic_t refcount; /* userfaultfd syscall flags */ unsigned int flags; + /* features requested from the userspace */ + unsigned int features; /* state machine */ enum userfaultfd_state state; /* released */ @@ -59,6 +65,12 @@ struct userfaultfd_ctx { struct mm_struct *mm; }; +struct userfaultfd_fork_ctx { + struct userfaultfd_ctx *orig; + struct userfaultfd_ctx *new; + struct list_head list; +}; + struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_t wq; @@ -142,6 +154,8 @@ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); + VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); + VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); @@ -169,7 +183,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address, msg.arg.pagefault.address = address; if (flags & FAULT_FLAG_WRITE) /* - * If UFFD_FEATURE_PAGEFAULT_FLAG_WRITE was set in the + * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE * was not set in a UFFD_EVENT_PAGEFAULT, it means it * was a read fault, otherwise if set it means it's @@ -188,6 +202,49 @@ static inline struct uffd_msg userfault_msg(unsigned long address, return msg; } +#ifdef CONFIG_HUGETLB_PAGE +/* + * Same functionality as userfaultfd_must_wait below with modifications for + * hugepmd ranges. + */ +static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + unsigned long address, + unsigned long flags, + unsigned long reason) +{ + struct mm_struct *mm = ctx->mm; + pte_t *pte; + bool ret = true; + + VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); + + pte = huge_pte_offset(mm, address); + if (!pte) + goto out; + + ret = false; + + /* + * Lockless access: we're in a wait_event so it's ok if it + * changes under us. + */ + if (huge_pte_none(*pte)) + ret = true; + if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP)) + ret = true; +out: + return ret; +} +#else +static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + unsigned long address, + unsigned long flags, + unsigned long reason) +{ + return false; /* should never get here */ +} +#endif /* CONFIG_HUGETLB_PAGE */ + /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any @@ -364,8 +421,12 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) set_current_state(blocking_state); spin_unlock(&ctx->fault_pending_wqh.lock); - must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, - reason); + if (!is_vm_hugetlb_page(vmf->vma)) + must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, + reason); + else + must_wait = userfaultfd_huge_must_wait(ctx, vmf->address, + vmf->flags, reason); up_read(&mm->mmap_sem); if (likely(must_wait && !ACCESS_ONCE(ctx->released) && @@ -458,6 +519,196 @@ out: return ret; } +static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, + struct userfaultfd_wait_queue *ewq) +{ + int ret = 0; + + ewq->ctx = ctx; + init_waitqueue_entry(&ewq->wq, current); + + spin_lock(&ctx->event_wqh.lock); + /* + * After the __add_wait_queue the uwq is visible to userland + * through poll/read(). + */ + __add_wait_queue(&ctx->event_wqh, &ewq->wq); + for (;;) { + set_current_state(TASK_KILLABLE); + if (ewq->msg.event == 0) + break; + if (ACCESS_ONCE(ctx->released) || + fatal_signal_pending(current)) { + ret = -1; + __remove_wait_queue(&ctx->event_wqh, &ewq->wq); + break; + } + + spin_unlock(&ctx->event_wqh.lock); + + wake_up_poll(&ctx->fd_wqh, POLLIN); + schedule(); + + spin_lock(&ctx->event_wqh.lock); + } + __set_current_state(TASK_RUNNING); + spin_unlock(&ctx->event_wqh.lock); + + /* + * ctx may go away after this if the userfault pseudo fd is + * already released. + */ + + userfaultfd_ctx_put(ctx); + return ret; +} + +static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, + struct userfaultfd_wait_queue *ewq) +{ + ewq->msg.event = 0; + wake_up_locked(&ctx->event_wqh); + __remove_wait_queue(&ctx->event_wqh, &ewq->wq); +} + +int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) +{ + struct userfaultfd_ctx *ctx = NULL, *octx; + struct userfaultfd_fork_ctx *fctx; + + octx = vma->vm_userfaultfd_ctx.ctx; + if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { + vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + return 0; + } + + list_for_each_entry(fctx, fcs, list) + if (fctx->orig == octx) { + ctx = fctx->new; + break; + } + + if (!ctx) { + fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); + if (!fctx) + return -ENOMEM; + + ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); + if (!ctx) { + kfree(fctx); + return -ENOMEM; + } + + atomic_set(&ctx->refcount, 1); + ctx->flags = octx->flags; + ctx->state = UFFD_STATE_RUNNING; + ctx->features = octx->features; + ctx->released = false; + ctx->mm = vma->vm_mm; + atomic_inc(&ctx->mm->mm_count); + + userfaultfd_ctx_get(octx); + fctx->orig = octx; + fctx->new = ctx; + list_add_tail(&fctx->list, fcs); + } + + vma->vm_userfaultfd_ctx.ctx = ctx; + return 0; +} + +static int dup_fctx(struct userfaultfd_fork_ctx *fctx) +{ + struct userfaultfd_ctx *ctx = fctx->orig; + struct userfaultfd_wait_queue ewq; + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_FORK; + ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; + + return userfaultfd_event_wait_completion(ctx, &ewq); +} + +void dup_userfaultfd_complete(struct list_head *fcs) +{ + int ret = 0; + struct userfaultfd_fork_ctx *fctx, *n; + + list_for_each_entry_safe(fctx, n, fcs, list) { + if (!ret) + ret = dup_fctx(fctx); + list_del(&fctx->list); + kfree(fctx); + } +} + +void mremap_userfaultfd_prep(struct vm_area_struct *vma, + struct vm_userfaultfd_ctx *vm_ctx) +{ + struct userfaultfd_ctx *ctx; + + ctx = vma->vm_userfaultfd_ctx.ctx; + if (ctx && (ctx->features & UFFD_FEATURE_EVENT_REMAP)) { + vm_ctx->ctx = ctx; + userfaultfd_ctx_get(ctx); + } +} + +void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, + unsigned long from, unsigned long to, + unsigned long len) +{ + struct userfaultfd_ctx *ctx = vm_ctx->ctx; + struct userfaultfd_wait_queue ewq; + + if (!ctx) + return; + + if (to & ~PAGE_MASK) { + userfaultfd_ctx_put(ctx); + return; + } + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_REMAP; + ewq.msg.arg.remap.from = from; + ewq.msg.arg.remap.to = to; + ewq.msg.arg.remap.len = len; + + userfaultfd_event_wait_completion(ctx, &ewq); +} + +void madvise_userfault_dontneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + struct mm_struct *mm = vma->vm_mm; + struct userfaultfd_ctx *ctx; + struct userfaultfd_wait_queue ewq; + + ctx = vma->vm_userfaultfd_ctx.ctx; + if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_MADVDONTNEED)) + return; + + userfaultfd_ctx_get(ctx); + up_read(&mm->mmap_sem); + + *prev = NULL; /* We wait for ACK w/o the mmap semaphore */ + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_MADVDONTNEED; + ewq.msg.arg.madv_dn.start = start; + ewq.msg.arg.madv_dn.end = end; + + userfaultfd_event_wait_completion(ctx, &ewq); + + down_read(&mm->mmap_sem); +} + static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; @@ -522,25 +773,36 @@ wakeup: } /* fault_pending_wqh.lock must be hold by the caller */ -static inline struct userfaultfd_wait_queue *find_userfault( - struct userfaultfd_ctx *ctx) +static inline struct userfaultfd_wait_queue *find_userfault_in( + wait_queue_head_t *wqh) { wait_queue_t *wq; struct userfaultfd_wait_queue *uwq; - VM_BUG_ON(!spin_is_locked(&ctx->fault_pending_wqh.lock)); + VM_BUG_ON(!spin_is_locked(&wqh->lock)); uwq = NULL; - if (!waitqueue_active(&ctx->fault_pending_wqh)) + if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ - wq = list_last_entry(&ctx->fault_pending_wqh.task_list, - typeof(*wq), task_list); + wq = list_last_entry(&wqh->task_list, typeof(*wq), task_list); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } +static inline struct userfaultfd_wait_queue *find_userfault( + struct userfaultfd_ctx *ctx) +{ + return find_userfault_in(&ctx->fault_pending_wqh); +} + +static inline struct userfaultfd_wait_queue *find_userfault_evt( + struct userfaultfd_ctx *ctx) +{ + return find_userfault_in(&ctx->event_wqh); +} + static unsigned int userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; @@ -572,10 +834,42 @@ static unsigned int userfaultfd_poll(struct file *file, poll_table *wait) smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = POLLIN; + else if (waitqueue_active(&ctx->event_wqh)) + ret = POLLIN; + return ret; default: - BUG(); + WARN_ON_ONCE(1); + return POLLERR; + } +} + +static const struct file_operations userfaultfd_fops; + +static int resolve_userfault_fork(struct userfaultfd_ctx *ctx, + struct userfaultfd_ctx *new, + struct uffd_msg *msg) +{ + int fd; + struct file *file; + unsigned int flags = new->flags & UFFD_SHARED_FCNTL_FLAGS; + + fd = get_unused_fd_flags(flags); + if (fd < 0) + return fd; + + file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, new, + O_RDWR | flags); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); } + + fd_install(fd, file); + msg->arg.reserved.reserved1 = 0; + msg->arg.fork.ufd = fd; + + return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, @@ -584,6 +878,15 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; + /* + * Handling fork event requires sleeping operations, so + * we drop the event_wqh lock, then do these ops, then + * lock it back and wake up the waiter. While the lock is + * dropped the ewq may go away so we keep track of it + * carefully. + */ + LIST_HEAD(fork_event); + struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock(&ctx->fd_wqh.lock); @@ -635,6 +938,29 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, break; } spin_unlock(&ctx->fault_pending_wqh.lock); + + spin_lock(&ctx->event_wqh.lock); + uwq = find_userfault_evt(ctx); + if (uwq) { + *msg = uwq->msg; + + if (uwq->msg.event == UFFD_EVENT_FORK) { + fork_nctx = (struct userfaultfd_ctx *) + (unsigned long) + uwq->msg.arg.reserved.reserved1; + list_move(&uwq->wq.task_list, &fork_event); + spin_unlock(&ctx->event_wqh.lock); + ret = 0; + break; + } + + userfaultfd_event_complete(ctx, uwq); + spin_unlock(&ctx->event_wqh.lock); + ret = 0; + break; + } + spin_unlock(&ctx->event_wqh.lock); + if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -651,6 +977,23 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, __set_current_state(TASK_RUNNING); spin_unlock(&ctx->fd_wqh.lock); + if (!ret && msg->event == UFFD_EVENT_FORK) { + ret = resolve_userfault_fork(ctx, fork_nctx, msg); + + if (!ret) { + spin_lock(&ctx->event_wqh.lock); + if (!list_empty(&fork_event)) { + uwq = list_first_entry(&fork_event, + typeof(*uwq), + wq.task_list); + list_del(&uwq->wq.task_list); + __add_wait_queue(&ctx->event_wqh, &uwq->wq); + userfaultfd_event_complete(ctx, uwq); + } + spin_unlock(&ctx->event_wqh.lock); + } + } + return ret; } @@ -753,6 +1096,12 @@ static __always_inline int validate_range(struct mm_struct *mm, return 0; } +static inline bool vma_can_userfault(struct vm_area_struct *vma) +{ + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { @@ -763,6 +1112,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; + bool non_anon_pages; unsigned long start, end, vma_end; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -814,13 +1164,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out_unlock; /* + * If the first vma contains huge pages, make sure start address + * is aligned to huge page size. + */ + if (is_vm_hugetlb_page(vma)) { + unsigned long vma_hpagesize = vma_kernel_pagesize(vma); + + if (start & (vma_hpagesize - 1)) + goto out_unlock; + } + + /* * Search for not compatible vmas. - * - * FIXME: this shall be relaxed later so that it doesn't fail - * on tmpfs backed vmas (in addition to the current allowance - * on anonymous vmas). */ found = false; + non_anon_pages = false; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); @@ -829,8 +1187,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, /* check not compatible vmas */ ret = -EINVAL; - if (cur->vm_ops) + if (!vma_can_userfault(cur)) goto out_unlock; + /* + * If this vma contains ending address, and huge pages + * check alignment. + */ + if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && + end > cur->vm_start) { + unsigned long vma_hpagesize = vma_kernel_pagesize(cur); + + ret = -EINVAL; + + if (end & (vma_hpagesize - 1)) + goto out_unlock; + } /* * Check that this vma isn't already owned by a @@ -843,6 +1214,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; + /* + * Note vmas containing huge pages + */ + if (is_vm_hugetlb_page(cur) || vma_is_shmem(cur)) + non_anon_pages = true; + found = true; } BUG_ON(!found); @@ -854,7 +1231,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, do { cond_resched(); - BUG_ON(vma->vm_ops); + BUG_ON(!vma_can_userfault(vma)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); @@ -912,7 +1289,8 @@ out_unlock: * userland which ioctls methods are guaranteed to * succeed on this range. */ - if (put_user(UFFD_API_RANGE_IOCTLS, + if (put_user(non_anon_pages ? UFFD_API_RANGE_IOCTLS_BASIC : + UFFD_API_RANGE_IOCTLS, &user_uffdio_register->ioctls)) ret = -EFAULT; } @@ -959,11 +1337,18 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out_unlock; /* + * If the first vma contains huge pages, make sure start address + * is aligned to huge page size. + */ + if (is_vm_hugetlb_page(vma)) { + unsigned long vma_hpagesize = vma_kernel_pagesize(vma); + + if (start & (vma_hpagesize - 1)) + goto out_unlock; + } + + /* * Search for not compatible vmas. - * - * FIXME: this shall be relaxed later so that it doesn't fail - * on tmpfs backed vmas (in addition to the current allowance - * on anonymous vmas). */ found = false; ret = -EINVAL; @@ -980,7 +1365,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * provides for more strict behavior to notice * unregistration errors. */ - if (cur->vm_ops) + if (!vma_can_userfault(cur)) goto out_unlock; found = true; @@ -994,7 +1379,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, do { cond_resched(); - BUG_ON(vma->vm_ops); + BUG_ON(!vma_can_userfault(vma)); /* * Nothing to do: this vma is already registered into this @@ -1007,6 +1392,19 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, start = vma->vm_start; vma_end = min(end, vma->vm_end); + if (userfaultfd_missing(vma)) { + /* + * Wake any concurrent pending userfault while + * we unregister, so they will not hang + * permanently and it avoids userland to call + * UFFDIO_WAKE explicitly. + */ + struct userfaultfd_wake_range range; + range.start = start; + range.len = vma_end - start; + wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); + } + new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, @@ -1178,6 +1576,14 @@ out: return ret; } +static inline unsigned int uffd_ctx_features(__u64 user_features) +{ + /* + * For the current set of features the bits just coincide + */ + return (unsigned int)user_features; +} + /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API @@ -1189,6 +1595,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; int ret; + __u64 features; ret = -EINVAL; if (ctx->state != UFFD_STATE_WAIT_API) @@ -1196,19 +1603,23 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - if (uffdio_api.api != UFFD_API || uffdio_api.features) { + features = uffdio_api.features; + if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) { memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; ret = -EINVAL; goto out; } + /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; ctx->state = UFFD_STATE_RUNNING; + /* only enable the requested features for this uffd context */ + ctx->features = uffd_ctx_features(features); ret = 0; out: return ret; @@ -1295,6 +1706,7 @@ static void init_once_userfaultfd_ctx(void *mem) init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); + init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_init(&ctx->refile_seq); } @@ -1335,6 +1747,7 @@ static struct file *userfaultfd_file_create(int flags) atomic_set(&ctx->refcount, 1); ctx->flags = flags; + ctx->features = 0; ctx->state = UFFD_STATE_WAIT_API; ctx->released = false; ctx->mm = current->mm; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 9f06a211e157..369adcc18c02 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -221,20 +221,22 @@ xfs_alloc_get_rec( * Compute aligned version of the found extent. * Takes alignment and min length into account. */ -STATIC void +STATIC bool xfs_alloc_compute_aligned( xfs_alloc_arg_t *args, /* allocation argument structure */ xfs_agblock_t foundbno, /* starting block in found extent */ xfs_extlen_t foundlen, /* length in found extent */ xfs_agblock_t *resbno, /* result block number */ - xfs_extlen_t *reslen) /* result length */ + xfs_extlen_t *reslen, /* result length */ + unsigned *busy_gen) { - xfs_agblock_t bno; - xfs_extlen_t len; + xfs_agblock_t bno = foundbno; + xfs_extlen_t len = foundlen; xfs_extlen_t diff; + bool busy; /* Trim busy sections out of found extent */ - xfs_extent_busy_trim(args, foundbno, foundlen, &bno, &len); + busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen); /* * If we have a largish extent that happens to start before min_agbno, @@ -259,6 +261,8 @@ xfs_alloc_compute_aligned( *resbno = bno; *reslen = len; } + + return busy; } /* @@ -737,10 +741,11 @@ xfs_alloc_ag_vextent_exact( int error; xfs_agblock_t fbno; /* start block of found extent */ xfs_extlen_t flen; /* length of found extent */ - xfs_agblock_t tbno; /* start block of trimmed extent */ - xfs_extlen_t tlen; /* length of trimmed extent */ - xfs_agblock_t tend; /* end block of trimmed extent */ + xfs_agblock_t tbno; /* start block of busy extent */ + xfs_extlen_t tlen; /* length of busy extent */ + xfs_agblock_t tend; /* end block of busy extent */ int i; /* success/failure of operation */ + unsigned busy_gen; ASSERT(args->alignment == 1); @@ -773,7 +778,9 @@ xfs_alloc_ag_vextent_exact( /* * Check for overlapping busy extents. */ - xfs_extent_busy_trim(args, fbno, flen, &tbno, &tlen); + tbno = fbno; + tlen = flen; + xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen); /* * Give up if the start of the extent is busy, or the freespace isn't @@ -853,6 +860,7 @@ xfs_alloc_find_best_extent( xfs_agblock_t sdiff; int error; int i; + unsigned busy_gen; /* The good extent is perfect, no need to search. */ if (!gdiff) @@ -866,7 +874,8 @@ xfs_alloc_find_best_extent( if (error) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, *sbno, *slen, sbnoa, slena); + xfs_alloc_compute_aligned(args, *sbno, *slen, + sbnoa, slena, &busy_gen); /* * The good extent is closer than this one. @@ -955,7 +964,8 @@ xfs_alloc_ag_vextent_near( xfs_extlen_t ltlena; /* aligned ... */ xfs_agblock_t ltnew; /* useful start bno of left side */ xfs_extlen_t rlen; /* length of returned extent */ - int forced = 0; + bool busy; + unsigned busy_gen; #ifdef DEBUG /* * Randomly don't execute the first algorithm. @@ -982,6 +992,7 @@ restart: ltlen = 0; gtlena = 0; ltlena = 0; + busy = false; /* * Get a cursor for the by-size btree. @@ -1064,8 +1075,8 @@ restart: if ((error = xfs_alloc_get_rec(cnt_cur, <bno, <len, &i))) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, ltbno, ltlen, - <bnoa, <lena); + busy = xfs_alloc_compute_aligned(args, ltbno, ltlen, + <bnoa, <lena, &busy_gen); if (ltlena < args->minlen) continue; if (ltbnoa < args->min_agbno || ltbnoa > args->max_agbno) @@ -1183,8 +1194,8 @@ restart: if ((error = xfs_alloc_get_rec(bno_cur_lt, <bno, <len, &i))) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, ltbno, ltlen, - <bnoa, <lena); + busy |= xfs_alloc_compute_aligned(args, ltbno, ltlen, + <bnoa, <lena, &busy_gen); if (ltlena >= args->minlen && ltbnoa >= args->min_agbno) break; if ((error = xfs_btree_decrement(bno_cur_lt, 0, &i))) @@ -1199,8 +1210,8 @@ restart: if ((error = xfs_alloc_get_rec(bno_cur_gt, >bno, >len, &i))) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, gtbno, gtlen, - >bnoa, >lena); + busy |= xfs_alloc_compute_aligned(args, gtbno, gtlen, + >bnoa, >lena, &busy_gen); if (gtlena >= args->minlen && gtbnoa <= args->max_agbno) break; if ((error = xfs_btree_increment(bno_cur_gt, 0, &i))) @@ -1261,9 +1272,9 @@ restart: if (bno_cur_lt == NULL && bno_cur_gt == NULL) { xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); - if (!forced++) { + if (busy) { trace_xfs_alloc_near_busy(args); - xfs_log_force(args->mp, XFS_LOG_SYNC); + xfs_extent_busy_flush(args->mp, args->pag, busy_gen); goto restart; } trace_xfs_alloc_size_neither(args); @@ -1344,7 +1355,8 @@ xfs_alloc_ag_vextent_size( int i; /* temp status variable */ xfs_agblock_t rbno; /* returned block number */ xfs_extlen_t rlen; /* length of returned extent */ - int forced = 0; + bool busy; + unsigned busy_gen; restart: /* @@ -1353,6 +1365,7 @@ restart: cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, args->agno, XFS_BTNUM_CNT); bno_cur = NULL; + busy = false; /* * Look for an entry >= maxlen+alignment-1 blocks. @@ -1362,14 +1375,13 @@ restart: goto error0; /* - * If none or we have busy extents that we cannot allocate from, then - * we have to settle for a smaller extent. In the case that there are - * no large extents, this will return the last entry in the tree unless - * the tree is empty. In the case that there are only busy large - * extents, this will return the largest small extent unless there + * If none then we have to settle for a smaller extent. In the case that + * there are no large extents, this will return the last entry in the + * tree unless the tree is empty. In the case that there are only busy + * large extents, this will return the largest small extent unless there * are no smaller extents available. */ - if (!i || forced > 1) { + if (!i) { error = xfs_alloc_ag_vextent_small(args, cnt_cur, &fbno, &flen, &i); if (error) @@ -1380,13 +1392,11 @@ restart: return 0; } ASSERT(i == 1); - xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen); + busy = xfs_alloc_compute_aligned(args, fbno, flen, &rbno, + &rlen, &busy_gen); } else { /* * Search for a non-busy extent that is large enough. - * If we are at low space, don't check, or if we fall of - * the end of the btree, turn off the busy check and - * restart. */ for (;;) { error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i); @@ -1394,8 +1404,8 @@ restart: goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, fbno, flen, - &rbno, &rlen); + busy = xfs_alloc_compute_aligned(args, fbno, flen, + &rbno, &rlen, &busy_gen); if (rlen >= args->maxlen) break; @@ -1407,18 +1417,13 @@ restart: /* * Our only valid extents must have been busy. * Make it unbusy by forcing the log out and - * retrying. If we've been here before, forcing - * the log isn't making the extents available, - * which means they have probably been freed in - * this transaction. In that case, we have to - * give up on them and we'll attempt a minlen - * allocation the next time around. + * retrying. */ xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_busy(args); - if (!forced++) - xfs_log_force(args->mp, XFS_LOG_SYNC); + xfs_extent_busy_flush(args->mp, + args->pag, busy_gen); goto restart; } } @@ -1454,8 +1459,8 @@ restart: XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); if (flen < bestrlen) break; - xfs_alloc_compute_aligned(args, fbno, flen, - &rbno, &rlen); + busy = xfs_alloc_compute_aligned(args, fbno, flen, + &rbno, &rlen, &busy_gen); rlen = XFS_EXTLEN_MIN(args->maxlen, rlen); XFS_WANT_CORRUPTED_GOTO(args->mp, rlen == 0 || (rlen <= flen && rbno + rlen <= fbno + flen), @@ -1484,10 +1489,10 @@ restart: */ args->len = rlen; if (rlen < args->minlen) { - if (!forced++) { + if (busy) { xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_busy(args); - xfs_log_force(args->mp, XFS_LOG_SYNC); + xfs_extent_busy_flush(args->mp, args->pag, busy_gen); goto restart; } goto out_nominleft; @@ -2659,21 +2664,11 @@ xfs_alloc_vextent( args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno); args->type = XFS_ALLOCTYPE_NEAR_BNO; /* FALLTHROUGH */ - case XFS_ALLOCTYPE_ANY_AG: - case XFS_ALLOCTYPE_START_AG: case XFS_ALLOCTYPE_FIRST_AG: /* * Rotate through the allocation groups looking for a winner. */ - if (type == XFS_ALLOCTYPE_ANY_AG) { - /* - * Start with the last place we left off. - */ - args->agno = sagno = (mp->m_agfrotor / rotorstep) % - mp->m_sb.sb_agcount; - args->type = XFS_ALLOCTYPE_THIS_AG; - flags = XFS_ALLOC_FLAG_TRYLOCK; - } else if (type == XFS_ALLOCTYPE_FIRST_AG) { + if (type == XFS_ALLOCTYPE_FIRST_AG) { /* * Start with allocation group given by bno. */ @@ -2682,8 +2677,6 @@ xfs_alloc_vextent( sagno = 0; flags = 0; } else { - if (type == XFS_ALLOCTYPE_START_AG) - args->type = XFS_ALLOCTYPE_THIS_AG; /* * Start with the given allocation group. */ @@ -2751,7 +2744,7 @@ xfs_alloc_vextent( } xfs_perag_put(args->pag); } - if (bump_rotor || (type == XFS_ALLOCTYPE_ANY_AG)) { + if (bump_rotor) { if (args->agno == sagno) mp->m_agfrotor = (mp->m_agfrotor + 1) % (mp->m_sb.sb_agcount * rotorstep); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 1d0f48a501a3..2a8d0fa6fbbe 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -29,9 +29,7 @@ extern struct workqueue_struct *xfs_alloc_wq; /* * Freespace allocation types. Argument to xfs_alloc_[v]extent. */ -#define XFS_ALLOCTYPE_ANY_AG 0x01 /* allocate anywhere, use rotor */ #define XFS_ALLOCTYPE_FIRST_AG 0x02 /* ... start at ag 0 */ -#define XFS_ALLOCTYPE_START_AG 0x04 /* anywhere, start in this a.g. */ #define XFS_ALLOCTYPE_THIS_AG 0x08 /* anywhere in this a.g. */ #define XFS_ALLOCTYPE_START_BNO 0x10 /* near this block else anywhere */ #define XFS_ALLOCTYPE_NEAR_BNO 0x20 /* in this a.g. and near this block */ @@ -41,9 +39,7 @@ extern struct workqueue_struct *xfs_alloc_wq; typedef unsigned int xfs_alloctype_t; #define XFS_ALLOC_TYPES \ - { XFS_ALLOCTYPE_ANY_AG, "ANY_AG" }, \ { XFS_ALLOCTYPE_FIRST_AG, "FIRST_AG" }, \ - { XFS_ALLOCTYPE_START_AG, "START_AG" }, \ { XFS_ALLOCTYPE_THIS_AG, "THIS_AG" }, \ { XFS_ALLOCTYPE_START_BNO, "START_BNO" }, \ { XFS_ALLOCTYPE_NEAR_BNO, "NEAR_BNO" }, \ diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index bfc00de5c6f1..a9c66d47757a 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -740,15 +740,9 @@ xfs_bmap_extents_to_btree( * Fill in the root. */ block = ifp->if_broot; - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, - XFS_BMAP_CRC_MAGIC, 1, 1, ip->i_ino, - XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, - XFS_BMAP_MAGIC, 1, 1, ip->i_ino, + xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, + XFS_BTNUM_BMAP, 1, 1, ip->i_ino, XFS_BTREE_LONG_PTRS); - /* * Need a cursor. Can't allocate until bb_level is filled in. */ @@ -804,9 +798,7 @@ try_another_ag: */ ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(*firstblock == NULLFSBLOCK || - args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) || - (dfops->dop_low && - args.agno > XFS_FSB_TO_AGNO(mp, *firstblock))); + args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock)); *firstblock = cur->bc_private.b.firstblock = args.fsbno; cur->bc_private.b.allocated++; ip->i_d.di_nblocks++; @@ -817,13 +809,8 @@ try_another_ag: */ abp->b_ops = &xfs_bmbt_buf_ops; ablock = XFS_BUF_TO_BLOCK(abp); - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block_int(mp, ablock, abp->b_bn, - XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block_int(mp, ablock, abp->b_bn, - XFS_BMAP_MAGIC, 0, 0, ip->i_ino, + xfs_btree_init_block_int(mp, ablock, abp->b_bn, + XFS_BTNUM_BMAP, 0, 0, ip->i_ino, XFS_BTREE_LONG_PTRS); arp = XFS_BMBT_REC_ADDR(mp, ablock, 1); @@ -1278,7 +1265,6 @@ xfs_bmap_read_extents( /* REFERENCED */ xfs_extnum_t room; /* number of entries there's room for */ - bno = NULLFSBLOCK; mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); exntf = (whichfork != XFS_DATA_FORK) ? XFS_EXTFMT_NOSTATE : @@ -1291,9 +1277,7 @@ xfs_bmap_read_extents( ASSERT(level > 0); pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp); - ASSERT(bno != NULLFSBLOCK); - ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount); - ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks); + /* * Go down the tree until leaf level is reached, following the first * pointer (leftmost) at each level. @@ -1864,6 +1848,7 @@ xfs_bmap_add_extent_delay_real( */ trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); xfs_bmbt_set_startblock(ep, new->br_startblock); + xfs_bmbt_set_state(ep, new->br_state); trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); (*nextents)++; @@ -2202,6 +2187,7 @@ STATIC int /* error */ xfs_bmap_add_extent_unwritten_real( struct xfs_trans *tp, xfs_inode_t *ip, /* incore inode pointer */ + int whichfork, xfs_extnum_t *idx, /* extent number to update/insert */ xfs_btree_cur_t **curp, /* if *curp is null, not a btree */ xfs_bmbt_irec_t *new, /* new data to add to file extents */ @@ -2221,12 +2207,14 @@ xfs_bmap_add_extent_unwritten_real( /* left is 0, right is 1, prev is 2 */ int rval=0; /* return value (logging flags) */ int state = 0;/* state bits, accessed thru macros */ - struct xfs_mount *mp = tp->t_mountp; + struct xfs_mount *mp = ip->i_mount; *logflagsp = 0; cur = *curp; - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + ifp = XFS_IFORK_PTR(ip, whichfork); + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; ASSERT(*idx >= 0); ASSERT(*idx <= xfs_iext_count(ifp)); @@ -2285,7 +2273,7 @@ xfs_bmap_add_extent_unwritten_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (*idx < xfs_iext_count(&ip->i_df) - 1) { + if (*idx < xfs_iext_count(ifp) - 1) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT); if (isnullstartblock(RIGHT.br_startblock)) @@ -2325,7 +2313,8 @@ xfs_bmap_add_extent_unwritten_real( trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_remove(ip, *idx + 1, 2, state); - ip->i_d.di_nextents -= 2; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 2); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2368,7 +2357,8 @@ xfs_bmap_add_extent_unwritten_real( trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_remove(ip, *idx + 1, 1, state); - ip->i_d.di_nextents--; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2403,7 +2393,8 @@ xfs_bmap_add_extent_unwritten_real( xfs_bmbt_set_state(ep, newext); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_remove(ip, *idx + 1, 1, state); - ip->i_d.di_nextents--; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2515,7 +2506,8 @@ xfs_bmap_add_extent_unwritten_real( trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_insert(ip, *idx, 1, new, state); - ip->i_d.di_nextents++; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2593,7 +2585,8 @@ xfs_bmap_add_extent_unwritten_real( ++*idx; xfs_iext_insert(ip, *idx, 1, new, state); - ip->i_d.di_nextents++; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2641,7 +2634,8 @@ xfs_bmap_add_extent_unwritten_real( ++*idx; xfs_iext_insert(ip, *idx, 2, &r[0], state); - ip->i_d.di_nextents += 2; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 2); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2695,17 +2689,17 @@ xfs_bmap_add_extent_unwritten_real( } /* update reverse mappings */ - error = xfs_rmap_convert_extent(mp, dfops, ip, XFS_DATA_FORK, new); + error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new); if (error) goto done; /* convert to a btree if necessary */ - if (xfs_bmap_needs_btree(ip, XFS_DATA_FORK)) { + if (xfs_bmap_needs_btree(ip, whichfork)) { int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur, - 0, &tmp_logflags, XFS_DATA_FORK); + 0, &tmp_logflags, whichfork); *logflagsp |= tmp_logflags; if (error) goto done; @@ -2717,7 +2711,7 @@ xfs_bmap_add_extent_unwritten_real( *curp = cur; } - xfs_bmap_check_leaf_extents(*curp, ip, XFS_DATA_FORK); + xfs_bmap_check_leaf_extents(*curp, ip, whichfork); done: *logflagsp |= rval; return error; @@ -2809,7 +2803,8 @@ xfs_bmap_add_extent_hole_delay( oldlen = startblockval(left.br_startblock) + startblockval(new->br_startblock) + startblockval(right.br_startblock); - newlen = xfs_bmap_worst_indlen(ip, temp); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx), nullstartblock((int)newlen)); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); @@ -2830,7 +2825,8 @@ xfs_bmap_add_extent_hole_delay( xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), temp); oldlen = startblockval(left.br_startblock) + startblockval(new->br_startblock); - newlen = xfs_bmap_worst_indlen(ip, temp); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx), nullstartblock((int)newlen)); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); @@ -2846,7 +2842,8 @@ xfs_bmap_add_extent_hole_delay( temp = new->br_blockcount + right.br_blockcount; oldlen = startblockval(new->br_startblock) + startblockval(right.br_startblock); - newlen = xfs_bmap_worst_indlen(ip, temp); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx), new->br_startoff, nullstartblock((int)newlen), temp, right.br_state); @@ -2899,13 +2896,14 @@ xfs_bmap_add_extent_hole_real( ASSERT(!isnullstartblock(new->br_startblock)); ASSERT(!bma->cur || !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); - ASSERT(whichfork != XFS_COW_FORK); XFS_STATS_INC(mp, xs_add_exlist); state = 0; if (whichfork == XFS_ATTR_FORK) state |= BMAP_ATTRFORK; + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; /* * Check and set flags if this segment has a left neighbor. @@ -3822,17 +3820,13 @@ xfs_bmap_btalloc( * the first block that was allocated. */ ASSERT(*ap->firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, *ap->firstblock) == - XFS_FSB_TO_AGNO(mp, args.fsbno) || - (ap->dfops->dop_low && - XFS_FSB_TO_AGNO(mp, *ap->firstblock) < - XFS_FSB_TO_AGNO(mp, args.fsbno))); + XFS_FSB_TO_AGNO(mp, *ap->firstblock) <= + XFS_FSB_TO_AGNO(mp, args.fsbno)); ap->blkno = args.fsbno; if (*ap->firstblock == NULLFSBLOCK) *ap->firstblock = args.fsbno; - ASSERT(nullfb || fb_agno == args.agno || - (ap->dfops->dop_low && fb_agno < args.agno)); + ASSERT(nullfb || fb_agno <= args.agno); ap->length = args.len; if (!(ap->flags & XFS_BMAPI_COWFORK)) ap->ip->i_d.di_nblocks += args.len; @@ -4368,10 +4362,16 @@ xfs_bmapi_allocate( bma->got.br_state = XFS_EXT_NORM; /* - * A wasdelay extent has been initialized, so shouldn't be flagged - * as unwritten. + * In the data fork, a wasdelay extent has been initialized, so + * shouldn't be flagged as unwritten. + * + * For the cow fork, however, we convert delalloc reservations + * (extents allocated for speculative preallocation) to + * allocated unwritten extents, and only convert the unwritten + * extents to real extents when we're about to write the data. */ - if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) && + if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) && + (bma->flags & XFS_BMAPI_PREALLOC) && xfs_sb_version_hasextflgbit(&mp->m_sb)) bma->got.br_state = XFS_EXT_UNWRITTEN; @@ -4422,8 +4422,6 @@ xfs_bmapi_convert_unwritten( (XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT)) return 0; - ASSERT(whichfork != XFS_COW_FORK); - /* * Modify (by adding) the state flag, if writing. */ @@ -4448,8 +4446,8 @@ xfs_bmapi_convert_unwritten( return error; } - error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx, - &bma->cur, mval, bma->firstblock, bma->dfops, + error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork, + &bma->idx, &bma->cur, mval, bma->firstblock, bma->dfops, &tmp_logflags); /* * Log the inode core unconditionally in the unwritten extent conversion @@ -4458,8 +4456,12 @@ xfs_bmapi_convert_unwritten( * in the transaction for the sake of fsync(), even if nothing has * changed, because fsync() will not force the log for this transaction * unless it sees the inode pinned. + * + * Note: If we're only converting cow fork extents, there aren't + * any on-disk updates to make, so we don't need to log anything. */ - bma->logflags |= tmp_logflags | XFS_ILOG_CORE; + if (whichfork != XFS_COW_FORK) + bma->logflags |= tmp_logflags | XFS_ILOG_CORE; if (error) return error; @@ -4533,15 +4535,15 @@ xfs_bmapi_write( ASSERT(*nmap >= 1); ASSERT(*nmap <= XFS_BMAP_MAX_NMAP); ASSERT(!(flags & XFS_BMAPI_IGSTATE)); - ASSERT(tp != NULL); + ASSERT(tp != NULL || + (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) == + (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)); ASSERT(len > 0); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(!(flags & XFS_BMAPI_REMAP) || whichfork == XFS_DATA_FORK); ASSERT(!(flags & XFS_BMAPI_PREALLOC) || !(flags & XFS_BMAPI_REMAP)); ASSERT(!(flags & XFS_BMAPI_CONVERT) || !(flags & XFS_BMAPI_REMAP)); - ASSERT(!(flags & XFS_BMAPI_PREALLOC) || whichfork != XFS_COW_FORK); - ASSERT(!(flags & XFS_BMAPI_CONVERT) || whichfork != XFS_COW_FORK); /* zeroing is for currently only for data extents, not metadata */ ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) != @@ -4746,13 +4748,9 @@ error0: if (bma.cur) { if (!error) { ASSERT(*firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, *firstblock) == + XFS_FSB_TO_AGNO(mp, *firstblock) <= XFS_FSB_TO_AGNO(mp, - bma.cur->bc_private.b.firstblock) || - (dfops->dop_low && - XFS_FSB_TO_AGNO(mp, *firstblock) < - XFS_FSB_TO_AGNO(mp, - bma.cur->bc_private.b.firstblock))); + bma.cur->bc_private.b.firstblock)); *firstblock = bma.cur->bc_private.b.firstblock; } xfs_btree_del_cursor(bma.cur, @@ -4787,34 +4785,59 @@ xfs_bmap_split_indlen( xfs_filblks_t len2 = *indlen2; xfs_filblks_t nres = len1 + len2; /* new total res. */ xfs_filblks_t stolen = 0; + xfs_filblks_t resfactor; /* * Steal as many blocks as we can to try and satisfy the worst case * indlen for both new extents. */ - while (nres > ores && avail) { - nres--; - avail--; - stolen++; - } + if (ores < nres && avail) + stolen = XFS_FILBLKS_MIN(nres - ores, avail); + ores += stolen; + + /* nothing else to do if we've satisfied the new reservation */ + if (ores >= nres) + return stolen; + + /* + * We can't meet the total required reservation for the two extents. + * Calculate the percent of the overall shortage between both extents + * and apply this percentage to each of the requested indlen values. + * This distributes the shortage fairly and reduces the chances that one + * of the two extents is left with nothing when extents are repeatedly + * split. + */ + resfactor = (ores * 100); + do_div(resfactor, nres); + len1 *= resfactor; + do_div(len1, 100); + len2 *= resfactor; + do_div(len2, 100); + ASSERT(len1 + len2 <= ores); + ASSERT(len1 < *indlen1 && len2 < *indlen2); /* - * The only blocks available are those reserved for the original - * extent and what we can steal from the extent being removed. - * If this still isn't enough to satisfy the combined - * requirements for the two new extents, skim blocks off of each - * of the new reservations until they match what is available. + * Hand out the remainder to each extent. If one of the two reservations + * is zero, we want to make sure that one gets a block first. The loop + * below starts with len1, so hand len2 a block right off the bat if it + * is zero. */ - while (nres > ores) { - if (len1) { - len1--; - nres--; + ores -= (len1 + len2); + ASSERT((*indlen1 - len1) + (*indlen2 - len2) >= ores); + if (ores && !len2 && *indlen2) { + len2++; + ores--; + } + while (ores) { + if (len1 < *indlen1) { + len1++; + ores--; } - if (nres == ores) + if (!ores) break; - if (len2) { - len2--; - nres--; + if (len2 < *indlen2) { + len2++; + ores--; } } @@ -5556,8 +5579,8 @@ __xfs_bunmapi( } del.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, ip, - &lastx, &cur, &del, firstblock, dfops, - &logflags); + whichfork, &lastx, &cur, &del, + firstblock, dfops, &logflags); if (error) goto error0; goto nodelete; @@ -5610,8 +5633,9 @@ __xfs_bunmapi( prev.br_state = XFS_EXT_UNWRITTEN; lastx--; error = xfs_bmap_add_extent_unwritten_real(tp, - ip, &lastx, &cur, &prev, - firstblock, dfops, &logflags); + ip, whichfork, &lastx, &cur, + &prev, firstblock, dfops, + &logflags); if (error) goto error0; goto nodelete; @@ -5619,8 +5643,9 @@ __xfs_bunmapi( ASSERT(del.br_state == XFS_EXT_NORM); del.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, - ip, &lastx, &cur, &del, - firstblock, dfops, &logflags); + ip, whichfork, &lastx, &cur, + &del, firstblock, dfops, + &logflags); if (error) goto error0; goto nodelete; diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index d9be241fc86f..f93072b58a58 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -71,15 +71,9 @@ xfs_bmdr_to_bmbt( xfs_bmbt_key_t *tkp; __be64 *tpp; - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, - XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, - XFS_BMAP_MAGIC, 0, 0, ip->i_ino, + xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, + XFS_BTNUM_BMAP, 0, 0, ip->i_ino, XFS_BTREE_LONG_PTRS); - rblock->bb_level = dblock->bb_level; ASSERT(be16_to_cpu(rblock->bb_level) > 0); rblock->bb_numrecs = dblock->bb_numrecs; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 21e6a6ab6b9a..c3decedc9455 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -50,8 +50,18 @@ static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = { XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC, XFS_REFC_CRC_MAGIC } }; -#define xfs_btree_magic(cur) \ - xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum] + +__uint32_t +xfs_btree_magic( + int crc, + xfs_btnum_t btnum) +{ + __uint32_t magic = xfs_magics[crc][btnum]; + + /* Ensure we asked for crc for crc-only magics. */ + ASSERT(magic != 0); + return magic; +} STATIC int /* error (0 or EFSCORRUPTED) */ xfs_btree_check_lblock( @@ -62,10 +72,13 @@ xfs_btree_check_lblock( { int lblock_ok = 1; /* block passes checks */ struct xfs_mount *mp; /* file system mount point */ + xfs_btnum_t btnum = cur->bc_btnum; + int crc; mp = cur->bc_mp; + crc = xfs_sb_version_hascrc(&mp->m_sb); - if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (crc) { lblock_ok = lblock_ok && uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid) && @@ -74,7 +87,7 @@ xfs_btree_check_lblock( } lblock_ok = lblock_ok && - be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) && + be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) && be16_to_cpu(block->bb_level) == level && be16_to_cpu(block->bb_numrecs) <= cur->bc_ops->get_maxrecs(cur, level) && @@ -110,13 +123,16 @@ xfs_btree_check_sblock( struct xfs_agf *agf; /* ag. freespace structure */ xfs_agblock_t agflen; /* native ag. freespace length */ int sblock_ok = 1; /* block passes checks */ + xfs_btnum_t btnum = cur->bc_btnum; + int crc; mp = cur->bc_mp; + crc = xfs_sb_version_hascrc(&mp->m_sb); agbp = cur->bc_private.a.agbp; agf = XFS_BUF_TO_AGF(agbp); agflen = be32_to_cpu(agf->agf_length); - if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (crc) { sblock_ok = sblock_ok && uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid) && @@ -125,7 +141,7 @@ xfs_btree_check_sblock( } sblock_ok = sblock_ok && - be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) && + be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) && be16_to_cpu(block->bb_level) == level && be16_to_cpu(block->bb_numrecs) <= cur->bc_ops->get_maxrecs(cur, level) && @@ -810,7 +826,8 @@ xfs_btree_read_bufl( xfs_daddr_t d; /* real disk block address */ int error; - ASSERT(fsbno != NULLFSBLOCK); + if (!XFS_FSB_SANITY_CHECK(mp, fsbno)) + return -EFSCORRUPTED; d = XFS_FSB_TO_DADDR(mp, fsbno); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d, mp->m_bsize, lock, &bp, ops); @@ -1084,12 +1101,15 @@ xfs_btree_init_block_int( struct xfs_mount *mp, struct xfs_btree_block *buf, xfs_daddr_t blkno, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, unsigned int flags) { + int crc = xfs_sb_version_hascrc(&mp->m_sb); + __u32 magic = xfs_btree_magic(crc, btnum); + buf->bb_magic = cpu_to_be32(magic); buf->bb_level = cpu_to_be16(level); buf->bb_numrecs = cpu_to_be16(numrecs); @@ -1097,7 +1117,7 @@ xfs_btree_init_block_int( if (flags & XFS_BTREE_LONG_PTRS) { buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK); buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK); - if (flags & XFS_BTREE_CRC_BLOCKS) { + if (crc) { buf->bb_u.l.bb_blkno = cpu_to_be64(blkno); buf->bb_u.l.bb_owner = cpu_to_be64(owner); uuid_copy(&buf->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid); @@ -1110,7 +1130,7 @@ xfs_btree_init_block_int( buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK); buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK); - if (flags & XFS_BTREE_CRC_BLOCKS) { + if (crc) { buf->bb_u.s.bb_blkno = cpu_to_be64(blkno); buf->bb_u.s.bb_owner = cpu_to_be32(__owner); uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid); @@ -1123,14 +1143,14 @@ void xfs_btree_init_block( struct xfs_mount *mp, struct xfs_buf *bp, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, unsigned int flags) { xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn, - magic, level, numrecs, owner, flags); + btnum, level, numrecs, owner, flags); } STATIC void @@ -1140,7 +1160,7 @@ xfs_btree_init_block_cur( int level, int numrecs) { - __u64 owner; + __u64 owner; /* * we can pull the owner from the cursor right now as the different @@ -1154,7 +1174,7 @@ xfs_btree_init_block_cur( owner = cur->bc_private.a.agno; xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn, - xfs_btree_magic(cur), level, numrecs, + cur->bc_btnum, level, numrecs, owner, cur->bc_flags); } diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index b69b947c4c1b..4bb62580a7fd 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -76,6 +76,8 @@ union xfs_btree_rec { #define XFS_BTNUM_RMAP ((xfs_btnum_t)XFS_BTNUM_RMAPi) #define XFS_BTNUM_REFC ((xfs_btnum_t)XFS_BTNUM_REFCi) +__uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); + /* * For logging record fields. */ @@ -378,7 +380,7 @@ void xfs_btree_init_block( struct xfs_mount *mp, struct xfs_buf *bp, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, @@ -389,7 +391,7 @@ xfs_btree_init_block_int( struct xfs_mount *mp, struct xfs_btree_block *buf, xfs_daddr_t blkno, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, @@ -456,7 +458,7 @@ static inline int xfs_btree_get_level(struct xfs_btree_block *block) #define XFS_FILBLKS_MAX(a,b) max_t(xfs_filblks_t, (a), (b)) #define XFS_FSB_SANITY_CHECK(mp,fsb) \ - (XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \ + (fsb && XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \ XFS_FSB_TO_AGBNO(mp, fsb) < mp->m_sb.sb_agblocks) /* diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index f2dc1a950c85..1bdf2888295b 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2633,7 +2633,7 @@ out_free: /* * Readahead the dir/attr block. */ -xfs_daddr_t +int xfs_da_reada_buf( struct xfs_inode *dp, xfs_dablk_t bno, @@ -2664,7 +2664,5 @@ out_free: if (mapp != &map) kmem_free(mapp); - if (error) - return -1; - return mappedbno; + return error; } diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index 98c75cbe6ac2..4e29cb6a3627 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -201,7 +201,7 @@ int xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp, xfs_dablk_t bno, xfs_daddr_t mappedbno, struct xfs_buf **bpp, int whichfork, const struct xfs_buf_ops *ops); -xfs_daddr_t xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno, +int xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno, xfs_daddr_t mapped_bno, int whichfork, const struct xfs_buf_ops *ops); int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno, diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 75a557432d0f..bbd1238852b3 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -155,6 +155,42 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = { .verify_write = xfs_dir3_free_write_verify, }; +/* Everything ok in the free block header? */ +static bool +xfs_dir3_free_header_check( + struct xfs_inode *dp, + xfs_dablk_t fbno, + struct xfs_buf *bp) +{ + struct xfs_mount *mp = dp->i_mount; + unsigned int firstdb; + int maxbests; + + maxbests = dp->d_ops->free_max_bests(mp->m_dir_geo); + firstdb = (xfs_dir2_da_to_db(mp->m_dir_geo, fbno) - + xfs_dir2_byte_to_db(mp->m_dir_geo, XFS_DIR2_FREE_OFFSET)) * + maxbests; + if (xfs_sb_version_hascrc(&mp->m_sb)) { + struct xfs_dir3_free_hdr *hdr3 = bp->b_addr; + + if (be32_to_cpu(hdr3->firstdb) != firstdb) + return false; + if (be32_to_cpu(hdr3->nvalid) > maxbests) + return false; + if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused)) + return false; + } else { + struct xfs_dir2_free_hdr *hdr = bp->b_addr; + + if (be32_to_cpu(hdr->firstdb) != firstdb) + return false; + if (be32_to_cpu(hdr->nvalid) > maxbests) + return false; + if (be32_to_cpu(hdr->nvalid) < be32_to_cpu(hdr->nused)) + return false; + } + return true; +} static int __xfs_dir3_free_read( @@ -168,11 +204,22 @@ __xfs_dir3_free_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_free_buf_ops); + if (err || !*bpp) + return err; + + /* Check things that we can't do in the verifier. */ + if (!xfs_dir3_free_header_check(dp, fbno, *bpp)) { + xfs_buf_ioerror(*bpp, -EFSCORRUPTED); + xfs_verifier_error(*bpp); + xfs_trans_brelse(tp, *bpp); + return -EFSCORRUPTED; + } /* try read returns without an error or *bpp if it lands in a hole */ - if (!err && tp && *bpp) + if (tp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_FREE_BUF); - return err; + + return 0; } int diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index f272abff11e1..d41ade5d293e 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -51,8 +51,7 @@ xfs_ialloc_cluster_alignment( struct xfs_mount *mp) { if (xfs_sb_version_hasalign(&mp->m_sb) && - mp->m_sb.sb_inoalignmt >= - XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) + mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp)) return mp->m_sb.sb_inoalignmt; return 1; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 222e103356c6..25c1e078aef6 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -26,6 +26,7 @@ #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" +#include "xfs_btree.h" #include "xfs_bmap_btree.h" #include "xfs_bmap.h" #include "xfs_error.h" @@ -429,11 +430,13 @@ xfs_iformat_btree( /* REFERENCED */ int nrecs; int size; + int level; ifp = XFS_IFORK_PTR(ip, whichfork); dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork); size = XFS_BMAP_BROOT_SPACE(mp, dfp); nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); /* * blow out if -- fork has less extents than can fit in @@ -446,7 +449,8 @@ xfs_iformat_btree( XFS_IFORK_MAXEXT(ip, whichfork) || XFS_BMDR_SPACE_CALC(nrecs) > XFS_DFORK_SIZE(dip, mp, whichfork) || - XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) { + XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks) || + level == 0 || level > XFS_BTREE_MAXLEVELS) { xfs_warn(mp, "corrupt inode %Lu (btree).", (unsigned long long) ip->i_ino); XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW, @@ -497,15 +501,14 @@ xfs_iread_extents( * We know that the size is valid (it's checked in iformat_btree) */ ifp->if_bytes = ifp->if_real_bytes = 0; - ifp->if_flags |= XFS_IFEXTENTS; xfs_iext_add(ifp, 0, nextents); error = xfs_bmap_read_extents(tp, ip, whichfork); if (error) { xfs_iext_destroy(ifp); - ifp->if_flags &= ~XFS_IFEXTENTS; return error; } xfs_validate_extents(ifp, nextents, XFS_EXTFMT_INODE(ip)); + ifp->if_flags |= XFS_IFEXTENTS; return 0; } /* diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index d9f65e2d5cc8..29a01ec89dd0 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -42,7 +42,6 @@ typedef struct xlog_recover_item { xfs_log_iovec_t *ri_buf; /* ptr to regions buffer */ } xlog_recover_item_t; -struct xlog_tid; typedef struct xlog_recover { struct hlist_node r_list; xlog_tid_t r_log_tid; /* log's transaction id */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 631e7c0e0a29..1ff9df7a3ce8 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -481,6 +481,12 @@ xfs_submit_ioend( struct xfs_ioend *ioend, int status) { + /* Convert CoW extents to regular */ + if (!status && ioend->io_type == XFS_IO_COW) { + status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode), + ioend->io_offset, ioend->io_size); + } + /* Reserve log space if we might write beyond the on-disk inode size. */ if (!status && ioend->io_type != XFS_IO_UNWRITTEN && diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index c1417919ab0a..8b75dcea5966 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -88,7 +88,6 @@ int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ { - xfs_alloctype_t atype = 0; /* type for allocation routines */ int error; /* error return value */ xfs_mount_t *mp; /* mount point structure */ xfs_extlen_t prod = 0; /* product factor for allocators */ @@ -155,18 +154,14 @@ xfs_bmap_rtalloc( /* * Realtime allocation, done through xfs_rtallocate_extent. */ - atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO; do_div(ap->blkno, mp->m_sb.sb_rextsize); rtb = ap->blkno; ap->length = ralen; - if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length, - &ralen, atype, ap->wasdel, prod, &rtb))) - return error; - if (rtb == NULLFSBLOCK && prod > 1 && - (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, - ap->length, &ralen, atype, - ap->wasdel, 1, &rtb))) + error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length, + &ralen, ap->wasdel, prod, &rtb); + if (error) return error; + ap->blkno = rtb; if (ap->blkno != NULLFSBLOCK) { ap->blkno *= mp->m_sb.sb_rextsize; @@ -787,11 +782,9 @@ xfs_getbmap( xfs_iunlock(ip, XFS_IOLOCK_SHARED); for (i = 0; i < cur_ext; i++) { - int full = 0; /* user array is full */ - /* format results & advance arg */ - error = formatter(&arg, &out[i], &full); - if (error || full) + error = formatter(&arg, &out[i]); + if (error) break; } @@ -917,17 +910,18 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force) */ int xfs_free_eofblocks( - xfs_mount_t *mp, - xfs_inode_t *ip, - bool need_iolock) + struct xfs_inode *ip) { - xfs_trans_t *tp; - int error; - xfs_fileoff_t end_fsb; - xfs_fileoff_t last_fsb; - xfs_filblks_t map_len; - int nimaps; - xfs_bmbt_irec_t imap; + struct xfs_trans *tp; + int error; + xfs_fileoff_t end_fsb; + xfs_fileoff_t last_fsb; + xfs_filblks_t map_len; + int nimaps; + struct xfs_bmbt_irec imap; + struct xfs_mount *mp = ip->i_mount; + + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); /* * Figure out if there are any blocks beyond the end @@ -944,6 +938,10 @@ xfs_free_eofblocks( error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0); xfs_iunlock(ip, XFS_ILOCK_SHARED); + /* + * If there are blocks after the end of file, truncate the file to its + * current size to free them up. + */ if (!error && (nimaps != 0) && (imap.br_startblock != HOLESTARTBLOCK || ip->i_delayed_blks)) { @@ -954,22 +952,13 @@ xfs_free_eofblocks( if (error) return error; - /* - * There are blocks after the end of file. - * Free them up now by truncating the file to - * its current size. - */ - if (need_iolock) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) - return -EAGAIN; - } + /* wait on dio to ensure i_size has settled */ + inode_dio_wait(VFS_I(ip)); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { ASSERT(XFS_FORCED_SHUTDOWN(mp)); - if (need_iolock) - xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } @@ -997,8 +986,6 @@ xfs_free_eofblocks( } xfs_iunlock(ip, XFS_ILOCK_EXCL); - if (need_iolock) - xfs_iunlock(ip, XFS_IOLOCK_EXCL); } return error; } @@ -1393,10 +1380,16 @@ xfs_shift_file_space( xfs_fileoff_t stop_fsb; xfs_fileoff_t next_fsb; xfs_fileoff_t shift_fsb; + uint resblks; ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT); if (direction == SHIFT_LEFT) { + /* + * Reserve blocks to cover potential extent merges after left + * shift operations. + */ + resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); next_fsb = XFS_B_TO_FSB(mp, offset + len); stop_fsb = XFS_B_TO_FSB(mp, VFS_I(ip)->i_size); } else { @@ -1404,6 +1397,7 @@ xfs_shift_file_space( * If right shift, delegate the work of initialization of * next_fsb to xfs_bmap_shift_extent as it has ilock held. */ + resblks = 0; next_fsb = NULLFSBLOCK; stop_fsb = XFS_B_TO_FSB(mp, offset); } @@ -1415,7 +1409,7 @@ xfs_shift_file_space( * into the accessible region of the file. */ if (xfs_can_free_eofblocks(ip, true)) { - error = xfs_free_eofblocks(mp, ip, false); + error = xfs_free_eofblocks(ip); if (error) return error; } @@ -1445,21 +1439,14 @@ xfs_shift_file_space( } while (!error && !done) { - /* - * We would need to reserve permanent block for transaction. - * This will come into picture when after shifting extent into - * hole we found that adjacent extents can be merged which - * may lead to freeing of a block during record update. - */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, - XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, + &tp); if (error) break; xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, - ip->i_gdquot, ip->i_pdquot, - XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, + ip->i_gdquot, ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS); if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 68a621a8e0c0..135d8267e284 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -35,7 +35,7 @@ int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, xfs_fileoff_t start_fsb, xfs_fileoff_t length); /* bmap to userspace formatter - copy to user & advance pointer */ -typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *, int *); +typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *); int xfs_getbmap(struct xfs_inode *ip, struct getbmapx *bmv, xfs_bmap_format_t formatter, void *arg); @@ -63,8 +63,7 @@ int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset, /* EOF block manipulation functions */ bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force); -int xfs_free_eofblocks(struct xfs_mount *mp, struct xfs_inode *ip, - bool need_iolock); +int xfs_free_eofblocks(struct xfs_inode *ip); int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip, struct xfs_swapext *sx); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 2975cb2319f4..0306168af332 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -1162,6 +1162,7 @@ xfs_buf_iodone_callbacks( */ bp->b_last_error = 0; bp->b_retries = 0; + bp->b_first_retry_time = 0; xfs_buf_do_callbacks(bp); bp->b_fspriv = NULL; diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 4ff499aa7338..d796ffac7296 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -208,32 +208,3 @@ xfs_ioc_trim( return -EFAULT; return 0; } - -int -xfs_discard_extents( - struct xfs_mount *mp, - struct list_head *list) -{ - struct xfs_extent_busy *busyp; - int error = 0; - - list_for_each_entry(busyp, list, list) { - trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, - busyp->length); - - error = blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, - XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), - XFS_FSB_TO_BB(mp, busyp->length), - GFP_NOFS, 0); - if (error && error != -EOPNOTSUPP) { - xfs_info(mp, - "discard failed for extent [0x%llx,%u], error %d", - (unsigned long long)busyp->bno, - busyp->length, - error); - return error; - } - } - - return 0; -} diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h index 344879aea646..0f070f9e44e1 100644 --- a/fs/xfs/xfs_discard.h +++ b/fs/xfs/xfs_discard.h @@ -5,6 +5,5 @@ struct fstrim_range; struct list_head; extern int xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *); -extern int xfs_discard_extents(struct xfs_mount *, struct list_head *); #endif /* XFS_DISCARD_H */ diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 162dc186cf04..77760dbf0242 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -45,18 +45,7 @@ xfs_extent_busy_insert( struct rb_node **rbp; struct rb_node *parent = NULL; - new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_MAYFAIL); - if (!new) { - /* - * No Memory! Since it is now not possible to track the free - * block, make this a synchronous transaction to insure that - * the block is not reused before this transaction commits. - */ - trace_xfs_extent_busy_enomem(tp->t_mountp, agno, bno, len); - xfs_trans_set_sync(tp); - return; - } - + new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_SLEEP); new->agno = agno; new->bno = bno; new->length = len; @@ -345,25 +334,31 @@ restart: * subset of the extent that is not busy. If *rlen is smaller than * args->minlen no suitable extent could be found, and the higher level * code needs to force out the log and retry the allocation. + * + * Return the current busy generation for the AG if the extent is busy. This + * value can be used to wait for at least one of the currently busy extents + * to be cleared. Note that the busy list is not guaranteed to be empty after + * the gen is woken. The state of a specific extent must always be confirmed + * with another call to xfs_extent_busy_trim() before it can be used. */ -void +bool xfs_extent_busy_trim( struct xfs_alloc_arg *args, - xfs_agblock_t bno, - xfs_extlen_t len, - xfs_agblock_t *rbno, - xfs_extlen_t *rlen) + xfs_agblock_t *bno, + xfs_extlen_t *len, + unsigned *busy_gen) { xfs_agblock_t fbno; xfs_extlen_t flen; struct rb_node *rbp; + bool ret = false; - ASSERT(len > 0); + ASSERT(*len > 0); spin_lock(&args->pag->pagb_lock); restart: - fbno = bno; - flen = len; + fbno = *bno; + flen = *len; rbp = args->pag->pagb_tree.rb_node; while (rbp && flen >= args->minlen) { struct xfs_extent_busy *busyp = @@ -515,24 +510,25 @@ restart: flen = fend - fbno; } - spin_unlock(&args->pag->pagb_lock); +out: - if (fbno != bno || flen != len) { - trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, + if (fbno != *bno || flen != *len) { + trace_xfs_extent_busy_trim(args->mp, args->agno, *bno, *len, fbno, flen); + *bno = fbno; + *len = flen; + *busy_gen = args->pag->pagb_gen; + ret = true; } - *rbno = fbno; - *rlen = flen; - return; + spin_unlock(&args->pag->pagb_lock); + return ret; fail: /* * Return a zero extent length as failure indications. All callers * re-check if the trimmed extent satisfies the minlen requirement. */ - spin_unlock(&args->pag->pagb_lock); - trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, fbno, 0); - *rbno = fbno; - *rlen = 0; + flen = 0; + goto out; } STATIC void @@ -551,6 +547,21 @@ xfs_extent_busy_clear_one( kmem_free(busyp); } +static void +xfs_extent_busy_put_pag( + struct xfs_perag *pag, + bool wakeup) + __releases(pag->pagb_lock) +{ + if (wakeup) { + pag->pagb_gen++; + wake_up_all(&pag->pagb_wait); + } + + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); +} + /* * Remove all extents on the passed in list from the busy extents tree. * If do_discard is set skip extents that need to be discarded, and mark @@ -565,27 +576,76 @@ xfs_extent_busy_clear( struct xfs_extent_busy *busyp, *n; struct xfs_perag *pag = NULL; xfs_agnumber_t agno = NULLAGNUMBER; + bool wakeup = false; list_for_each_entry_safe(busyp, n, list, list) { if (busyp->agno != agno) { - if (pag) { - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); - } - pag = xfs_perag_get(mp, busyp->agno); - spin_lock(&pag->pagb_lock); + if (pag) + xfs_extent_busy_put_pag(pag, wakeup); agno = busyp->agno; + pag = xfs_perag_get(mp, agno); + spin_lock(&pag->pagb_lock); + wakeup = false; } if (do_discard && busyp->length && - !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) + !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) { busyp->flags = XFS_EXTENT_BUSY_DISCARDED; - else + } else { xfs_extent_busy_clear_one(mp, pag, busyp); + wakeup = true; + } } - if (pag) { - spin_unlock(&pag->pagb_lock); + if (pag) + xfs_extent_busy_put_pag(pag, wakeup); +} + +/* + * Flush out all busy extents for this AG. + */ +void +xfs_extent_busy_flush( + struct xfs_mount *mp, + struct xfs_perag *pag, + unsigned busy_gen) +{ + DEFINE_WAIT (wait); + int log_flushed = 0, error; + + trace_xfs_log_force(mp, 0, _THIS_IP_); + error = _xfs_log_force(mp, XFS_LOG_SYNC, &log_flushed); + if (error) + return; + + do { + prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE); + if (busy_gen != READ_ONCE(pag->pagb_gen)) + break; + schedule(); + } while (1); + + finish_wait(&pag->pagb_wait, &wait); +} + +void +xfs_extent_busy_wait_all( + struct xfs_mount *mp) +{ + DEFINE_WAIT (wait); + xfs_agnumber_t agno; + + for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { + struct xfs_perag *pag = xfs_perag_get(mp, agno); + + do { + prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE); + if (RB_EMPTY_ROOT(&pag->pagb_tree)) + break; + schedule(); + } while (1); + finish_wait(&pag->pagb_wait, &wait); + xfs_perag_put(pag); } } @@ -596,9 +656,17 @@ xfs_extent_busy_clear( int xfs_extent_busy_ag_cmp( void *priv, - struct list_head *a, - struct list_head *b) + struct list_head *l1, + struct list_head *l2) { - return container_of(a, struct xfs_extent_busy, list)->agno - - container_of(b, struct xfs_extent_busy, list)->agno; + struct xfs_extent_busy *b1 = + container_of(l1, struct xfs_extent_busy, list); + struct xfs_extent_busy *b2 = + container_of(l2, struct xfs_extent_busy, list); + s32 diff; + + diff = b1->agno - b2->agno; + if (!diff) + diff = b1->bno - b2->bno; + return diff; } diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index bfff284d2dcc..60195ea1b84a 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -58,9 +58,16 @@ void xfs_extent_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata); +bool +xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno, + xfs_extlen_t *len, unsigned *busy_gen); + +void +xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag, + unsigned busy_gen); + void -xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t bno, - xfs_extlen_t len, xfs_agblock_t *rbno, xfs_extlen_t *rlen); +xfs_extent_busy_wait_all(struct xfs_mount *mp); int xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index bbb9eb6811b2..022014016d80 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -527,6 +527,15 @@ xfs_file_dio_aio_write( if ((iocb->ki_pos & mp->m_blockmask) || ((iocb->ki_pos + count) & mp->m_blockmask)) { unaligned_io = 1; + + /* + * We can't properly handle unaligned direct I/O to reflink + * files yet, as we can't unshare a partial block. + */ + if (xfs_is_reflink_inode(ip)) { + trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count); + return -EREMCHG; + } iolock = XFS_IOLOCK_EXCL; } else { iolock = XFS_IOLOCK_SHARED; @@ -552,14 +561,6 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos); - - /* If this is a block-aligned directio CoW, remap immediately. */ - if (xfs_is_reflink_inode(ip) && !unaligned_io) { - ret = xfs_reflink_allocate_cow_range(ip, iocb->ki_pos, count); - if (ret) - goto out; - } - ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io); out: xfs_iunlock(ip, iolock); @@ -614,8 +615,10 @@ xfs_file_buffered_aio_write( struct xfs_inode *ip = XFS_I(inode); ssize_t ret; int enospc = 0; - int iolock = XFS_IOLOCK_EXCL; + int iolock; +write_retry: + iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); ret = xfs_file_aio_write_checks(iocb, from, &iolock); @@ -625,7 +628,6 @@ xfs_file_buffered_aio_write( /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); -write_retry: trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos); ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops); if (likely(ret >= 0)) @@ -641,18 +643,21 @@ write_retry: * running at the same time. */ if (ret == -EDQUOT && !enospc) { + xfs_iunlock(ip, iolock); enospc = xfs_inode_free_quota_eofblocks(ip); if (enospc) goto write_retry; enospc = xfs_inode_free_quota_cowblocks(ip); if (enospc) goto write_retry; + iolock = 0; } else if (ret == -ENOSPC && !enospc) { struct xfs_eofblocks eofb = {0}; enospc = 1; xfs_flush_inodes(ip->i_mount); - eofb.eof_scan_owner = ip->i_ino; /* for locking */ + + xfs_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; xfs_icache_free_eofblocks(ip->i_mount, &eofb); goto write_retry; @@ -660,7 +665,8 @@ write_retry: current->backing_dev_info = NULL; out: - xfs_iunlock(ip, iolock); + if (iolock) + xfs_iunlock(ip, iolock); return ret; } @@ -908,9 +914,9 @@ xfs_dir_open( */ mode = xfs_ilock_data_map_shared(ip); if (ip->i_d.di_nextents > 0) - xfs_dir3_data_readahead(ip, 0, -1); + error = xfs_dir3_data_readahead(ip, 0, -1); xfs_iunlock(ip, mode); - return 0; + return error; } STATIC int @@ -1431,12 +1437,9 @@ xfs_filemap_fault( */ STATIC int xfs_filemap_pmd_fault( - struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags) + struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct xfs_inode *ip = XFS_I(inode); int ret; @@ -1445,16 +1448,16 @@ xfs_filemap_pmd_fault( trace_xfs_filemap_pmd_fault(ip); - if (flags & FAULT_FLAG_WRITE) { + if (vmf->flags & FAULT_FLAG_WRITE) { sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); } xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops); + ret = dax_iomap_pmd_fault(vmf, &xfs_iomap_ops); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - if (flags & FAULT_FLAG_WRITE) + if (vmf->flags & FAULT_FLAG_WRITE) sb_end_pagefault(inode->i_sb); return ret; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 242e8091296d..6ccaae9eb0ee 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -352,12 +352,7 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_ABTB_CRC_MAGIC, 0, 1, - agno, XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_ABTB_MAGIC, 0, 1, - agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, agno, 0); arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); @@ -381,12 +376,7 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_ABTC_CRC_MAGIC, 0, 1, - agno, XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_ABTC_MAGIC, 0, 1, - agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, agno, 0); arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); @@ -413,8 +403,8 @@ xfs_growfs_data_private( goto error0; } - xfs_btree_init_block(mp, bp, XFS_RMAP_CRC_MAGIC, 0, 0, - agno, XFS_BTREE_CRC_BLOCKS); + xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 0, + agno, 0); block = XFS_BUF_TO_BLOCK(bp); @@ -488,12 +478,7 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_IBT_CRC_MAGIC, 0, 0, - agno, XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_IBT_MAGIC, 0, 0, - agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_INO , 0, 0, agno, 0); error = xfs_bwrite(bp); xfs_buf_relse(bp); @@ -513,13 +498,8 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_FIBT_CRC_MAGIC, - 0, 0, agno, - XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_FIBT_MAGIC, 0, - 0, agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_FINO, + 0, 0, agno, 0); error = xfs_bwrite(bp); xfs_buf_relse(bp); @@ -540,9 +520,8 @@ xfs_growfs_data_private( goto error0; } - xfs_btree_init_block(mp, bp, XFS_REFC_CRC_MAGIC, - 0, 0, agno, - XFS_BTREE_CRC_BLOCKS); + xfs_btree_init_block(mp, bp, XFS_BTNUM_REFC, + 0, 0, agno, 0); error = xfs_bwrite(bp); xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 70ca4f608321..7234b9748c36 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1322,13 +1322,10 @@ xfs_inode_free_eofblocks( int flags, void *args) { - int ret; + int ret = 0; struct xfs_eofblocks *eofb = args; - bool need_iolock = true; int match; - ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0)); - if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); @@ -1356,21 +1353,19 @@ xfs_inode_free_eofblocks( if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; - - /* - * A scan owner implies we already hold the iolock. Skip it in - * xfs_free_eofblocks() to avoid deadlock. This also eliminates - * the possibility of EAGAIN being returned. - */ - if (eofb->eof_scan_owner == ip->i_ino) - need_iolock = false; } - ret = xfs_free_eofblocks(ip->i_mount, ip, need_iolock); - - /* don't revisit the inode if we're not waiting */ - if (ret == -EAGAIN && !(flags & SYNC_WAIT)) - ret = 0; + /* + * If the caller is waiting, return -EAGAIN to keep the background + * scanner moving and revisit the inode in a subsequent pass. + */ + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + if (flags & SYNC_WAIT) + ret = -EAGAIN; + return ret; + } + ret = xfs_free_eofblocks(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } @@ -1417,15 +1412,10 @@ __xfs_inode_free_quota_eofblocks( struct xfs_eofblocks eofb = {0}; struct xfs_dquot *dq; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); - /* - * Set the scan owner to avoid a potential livelock. Otherwise, the scan - * can repeatedly trylock on the inode we're currently processing. We - * run a sync scan to increase effectiveness and use the union filter to + * Run a sync scan to increase effectiveness and use the union filter to * cover all applicable quotas in a single scan. */ - eofb.eof_scan_owner = ip->i_ino; eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC; if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) { @@ -1577,12 +1567,9 @@ xfs_inode_free_cowblocks( { int ret; struct xfs_eofblocks *eofb = args; - bool need_iolock = true; int match; struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0)); - /* * Just clear the tag if we have an empty cow fork or none at all. It's * possible the inode was fully unshared since it was originally tagged. @@ -1615,28 +1602,16 @@ xfs_inode_free_cowblocks( if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; - - /* - * A scan owner implies we already hold the iolock. Skip it in - * xfs_free_eofblocks() to avoid deadlock. This also eliminates - * the possibility of EAGAIN being returned. - */ - if (eofb->eof_scan_owner == ip->i_ino) - need_iolock = false; } /* Free the CoW blocks */ - if (need_iolock) { - xfs_ilock(ip, XFS_IOLOCK_EXCL); - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - } + xfs_ilock(ip, XFS_IOLOCK_EXCL); + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF); - if (need_iolock) { - xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - } + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index a1e02f4708ab..8a7c849b4dea 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -27,7 +27,6 @@ struct xfs_eofblocks { kgid_t eof_gid; prid_t eof_prid; __u64 eof_min_file_size; - xfs_ino_t eof_scan_owner; }; #define SYNC_WAIT 0x0001 /* wait for i/o to complete */ @@ -102,7 +101,6 @@ xfs_fs_eofblocks_from_user( dst->eof_flags = src->eof_flags; dst->eof_prid = src->eof_prid; dst->eof_min_file_size = src->eof_min_file_size; - dst->eof_scan_owner = NULLFSINO; dst->eof_uid = INVALID_UID; if (src->eof_flags & XFS_EOF_FLAGS_UID) { diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index de32f0fe47c8..edfa6a55b064 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1692,32 +1692,34 @@ xfs_release( if (xfs_can_free_eofblocks(ip, false)) { /* + * Check if the inode is being opened, written and closed + * frequently and we have delayed allocation blocks outstanding + * (e.g. streaming writes from the NFS server), truncating the + * blocks past EOF will cause fragmentation to occur. + * + * In this case don't do the truncation, but we have to be + * careful how we detect this case. Blocks beyond EOF show up as + * i_delayed_blks even when the inode is clean, so we need to + * truncate them away first before checking for a dirty release. + * Hence on the first dirty close we will still remove the + * speculative allocation, but after that we will leave it in + * place. + */ + if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE)) + return 0; + /* * If we can't get the iolock just skip truncating the blocks * past EOF because we could deadlock with the mmap_sem - * otherwise. We'll get another chance to drop them once the + * otherwise. We'll get another chance to drop them once the * last reference to the inode is dropped, so we'll never leak * blocks permanently. - * - * Further, check if the inode is being opened, written and - * closed frequently and we have delayed allocation blocks - * outstanding (e.g. streaming writes from the NFS server), - * truncating the blocks past EOF will cause fragmentation to - * occur. - * - * In this case don't do the truncation, either, but we have to - * be careful how we detect this case. Blocks beyond EOF show - * up as i_delayed_blks even when the inode is clean, so we - * need to truncate them away first before checking for a dirty - * release. Hence on the first dirty close we will still remove - * the speculative allocation, but after that we will leave it - * in place. */ - if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE)) - return 0; - - error = xfs_free_eofblocks(mp, ip, true); - if (error && error != -EAGAIN) - return error; + if (xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + error = xfs_free_eofblocks(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); + if (error) + return error; + } /* delalloc blocks after truncation means it really is dirty */ if (ip->i_delayed_blks) @@ -1904,8 +1906,11 @@ xfs_inactive( * cache. Post-eof blocks must be freed, lest we end up with * broken free space accounting. */ - if (xfs_can_free_eofblocks(ip, true)) - xfs_free_eofblocks(mp, ip, false); + if (xfs_can_free_eofblocks(ip, true)) { + xfs_ilock(ip, XFS_IOLOCK_EXCL); + xfs_free_eofblocks(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); + } return; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index c67cfb451fd3..cf1363dbf32b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1524,7 +1524,7 @@ out_drop_write: } STATIC int -xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full) +xfs_getbmap_format(void **ap, struct getbmapx *bmv) { struct getbmap __user *base = (struct getbmap __user *)*ap; @@ -1567,7 +1567,7 @@ xfs_ioc_getbmap( } STATIC int -xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full) +xfs_getbmapx_format(void **ap, struct getbmapx *bmv) { struct getbmapx __user *base = (struct getbmapx __user *)*ap; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 1aa3abd67b36..41662fb14e87 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -162,7 +162,7 @@ xfs_iomap_write_direct( xfs_fileoff_t last_fsb; xfs_filblks_t count_fsb, resaligned; xfs_fsblock_t firstfsb; - xfs_extlen_t extsz, temp; + xfs_extlen_t extsz; int nimaps; int quota_flag; int rt; @@ -203,14 +203,7 @@ xfs_iomap_write_direct( } count_fsb = last_fsb - offset_fsb; ASSERT(count_fsb > 0); - - resaligned = count_fsb; - if (unlikely(extsz)) { - if ((temp = do_mod(offset_fsb, extsz))) - resaligned += temp; - if ((temp = do_mod(resaligned, extsz))) - resaligned += extsz - temp; - } + resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, extsz); if (unlikely(rt)) { resrtextents = qblocks = resaligned; @@ -685,7 +678,7 @@ xfs_iomap_write_allocate( int nres; if (whichfork == XFS_COW_FORK) - flags |= XFS_BMAPI_COWFORK; + flags |= XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC; /* * Make sure that the dquots are there. @@ -1002,47 +995,31 @@ xfs_file_iomap_begin( offset_fsb = XFS_B_TO_FSBT(mp, offset); end_fsb = XFS_B_TO_FSB(mp, offset + length); - if (xfs_is_reflink_inode(ip) && - (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) { - shared = xfs_reflink_find_cow_mapping(ip, offset, &imap); - if (shared) { - xfs_iunlock(ip, lockmode); - goto alloc_done; - } - ASSERT(!isnullstartblock(imap.br_startblock)); - } - error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); if (error) goto out_unlock; - if ((flags & IOMAP_REPORT) || - (xfs_is_reflink_inode(ip) && - (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) { + if (flags & IOMAP_REPORT) { /* Trim the mapping to the nearest shared extent boundary. */ error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); if (error) goto out_unlock; - - /* - * We're here because we're trying to do a directio write to a - * region that isn't aligned to a filesystem block. If the - * extent is shared, fall back to buffered mode to handle the - * RMW. - */ - if (!(flags & IOMAP_REPORT) && shared) { - trace_xfs_reflink_bounce_dio_write(ip, &imap); - error = -EREMCHG; - goto out_unlock; - } } if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { - error = xfs_reflink_reserve_cow(ip, &imap, &shared); - if (error) - goto out_unlock; + if (flags & IOMAP_DIRECT) { + /* may drop and re-acquire the ilock */ + error = xfs_reflink_allocate_cow(ip, &imap, &shared, + &lockmode); + if (error) + goto out_unlock; + } else { + error = xfs_reflink_reserve_cow(ip, &imap, &shared); + if (error) + goto out_unlock; + } end_fsb = imap.br_startoff + imap.br_blockcount; length = XFS_FSB_TO_B(mp, end_fsb) - offset; @@ -1071,7 +1048,6 @@ xfs_file_iomap_begin( if (error) return error; -alloc_done: iomap->flags = IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, length, 0, &imap); } else { @@ -1102,7 +1078,19 @@ xfs_file_iomap_end_delalloc( xfs_fileoff_t end_fsb; int error = 0; - start_fsb = XFS_B_TO_FSB(mp, offset + written); + /* behave as if the write failed if drop writes is enabled */ + if (xfs_mp_drop_writes(mp)) + written = 0; + + /* + * start_fsb refers to the first unused block after a short write. If + * nothing was written, round offset down to point at the first block in + * the range. + */ + if (unlikely(!written)) + start_fsb = XFS_B_TO_FSBT(mp, offset); + else + start_fsb = XFS_B_TO_FSB(mp, offset + written); end_fsb = XFS_B_TO_FSB(mp, offset + length); /* @@ -1114,6 +1102,9 @@ xfs_file_iomap_end_delalloc( * blocks in the range, they are ours. */ if (start_fsb < end_fsb) { + truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), + XFS_FSB_TO_B(mp, end_fsb) - 1); + xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_bmap_punch_delalloc_range(ip, start_fsb, end_fsb - start_fsb); @@ -1144,7 +1135,7 @@ xfs_file_iomap_end( return 0; } -struct iomap_ops xfs_iomap_ops = { +const struct iomap_ops xfs_iomap_ops = { .iomap_begin = xfs_file_iomap_begin, .iomap_end = xfs_file_iomap_end, }; @@ -1190,6 +1181,6 @@ out_unlock: return error; } -struct iomap_ops xfs_xattr_iomap_ops = { +const struct iomap_ops xfs_xattr_iomap_ops = { .iomap_begin = xfs_xattr_iomap_begin, }; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 6d45cf01fcff..00db3ecea084 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -33,7 +33,27 @@ void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); xfs_extlen_t xfs_eof_alignment(struct xfs_inode *ip, xfs_extlen_t extsize); -extern struct iomap_ops xfs_iomap_ops; -extern struct iomap_ops xfs_xattr_iomap_ops; +static inline xfs_filblks_t +xfs_aligned_fsb_count( + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + xfs_extlen_t extsz) +{ + if (extsz) { + xfs_extlen_t align; + + align = do_mod(offset_fsb, extsz); + if (align) + count_fsb += align; + align = do_mod(count_fsb, extsz); + if (align) + count_fsb += extsz - align; + } + + return count_fsb; +} + +extern const struct iomap_ops xfs_iomap_ops; +extern const struct iomap_ops xfs_xattr_iomap_ops; #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index b5e71072fde5..cc5a9f1574e7 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -124,7 +124,6 @@ struct xlog_ticket; struct xfs_log_item; struct xfs_item_ops; struct xfs_trans; -struct xfs_log_callback; xfs_lsn_t xfs_log_done(struct xfs_mount *mp, struct xlog_ticket *ticket, diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index a4ab192e1792..82f1cbcc4de1 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -30,6 +30,9 @@ #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" +#include "xfs_trace.h" + +struct workqueue_struct *xfs_discard_wq; /* * Allocate a new ticket. Failing to get a new ticket makes it really hard to @@ -491,6 +494,75 @@ xlog_cil_free_logvec( } } +static void +xlog_discard_endio_work( + struct work_struct *work) +{ + struct xfs_cil_ctx *ctx = + container_of(work, struct xfs_cil_ctx, discard_endio_work); + struct xfs_mount *mp = ctx->cil->xc_log->l_mp; + + xfs_extent_busy_clear(mp, &ctx->busy_extents, false); + kmem_free(ctx); +} + +/* + * Queue up the actual completion to a thread to avoid IRQ-safe locking for + * pagb_lock. Note that we need a unbounded workqueue, otherwise we might + * get the execution delayed up to 30 seconds for weird reasons. + */ +static void +xlog_discard_endio( + struct bio *bio) +{ + struct xfs_cil_ctx *ctx = bio->bi_private; + + INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work); + queue_work(xfs_discard_wq, &ctx->discard_endio_work); +} + +static void +xlog_discard_busy_extents( + struct xfs_mount *mp, + struct xfs_cil_ctx *ctx) +{ + struct list_head *list = &ctx->busy_extents; + struct xfs_extent_busy *busyp; + struct bio *bio = NULL; + struct blk_plug plug; + int error = 0; + + ASSERT(mp->m_flags & XFS_MOUNT_DISCARD); + + blk_start_plug(&plug); + list_for_each_entry(busyp, list, list) { + trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, + busyp->length); + + error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, + XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), + XFS_FSB_TO_BB(mp, busyp->length), + GFP_NOFS, 0, &bio); + if (error && error != -EOPNOTSUPP) { + xfs_info(mp, + "discard failed for extent [0x%llx,%u], error %d", + (unsigned long long)busyp->bno, + busyp->length, + error); + break; + } + } + + if (bio) { + bio->bi_private = ctx; + bio->bi_end_io = xlog_discard_endio; + submit_bio(bio); + } else { + xlog_discard_endio_work(&ctx->discard_endio_work); + } + blk_finish_plug(&plug); +} + /* * Mark all items committed and clear busy extents. We free the log vector * chains in a separate pass so that we unpin the log items as quickly as @@ -525,14 +597,10 @@ xlog_cil_committed( xlog_cil_free_logvec(ctx->lv_chain); - if (!list_empty(&ctx->busy_extents)) { - ASSERT(mp->m_flags & XFS_MOUNT_DISCARD); - - xfs_discard_extents(mp, &ctx->busy_extents); - xfs_extent_busy_clear(mp, &ctx->busy_extents, false); - } - - kmem_free(ctx); + if (!list_empty(&ctx->busy_extents)) + xlog_discard_busy_extents(mp, ctx); + else + kmem_free(ctx); } /* diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 2b6eec52178e..c2604a5366f2 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -257,6 +257,7 @@ struct xfs_cil_ctx { struct xfs_log_vec *lv_chain; /* logvecs being pushed */ struct xfs_log_callback log_cb; /* completion callback hook. */ struct list_head committing; /* ctx committing list */ + struct work_struct discard_endio_work; }; /* diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 9b9540db17a6..450bde68bb75 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -45,6 +45,7 @@ #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" #include "xfs_reflink.h" +#include "xfs_extent_busy.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); @@ -187,7 +188,7 @@ xfs_initialize_perag( xfs_agnumber_t *maxagi) { xfs_agnumber_t index; - xfs_agnumber_t first_initialised = 0; + xfs_agnumber_t first_initialised = NULLAGNUMBER; xfs_perag_t *pag; int error = -ENOMEM; @@ -202,22 +203,21 @@ xfs_initialize_perag( xfs_perag_put(pag); continue; } - if (!first_initialised) - first_initialised = index; pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); if (!pag) - goto out_unwind; + goto out_unwind_new_pags; pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); mutex_init(&pag->pag_ici_reclaim_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); if (xfs_buf_hash_init(pag)) - goto out_unwind; + goto out_free_pag; + init_waitqueue_head(&pag->pagb_wait); if (radix_tree_preload(GFP_NOFS)) - goto out_unwind; + goto out_hash_destroy; spin_lock(&mp->m_perag_lock); if (radix_tree_insert(&mp->m_perag_tree, index, pag)) { @@ -225,10 +225,13 @@ xfs_initialize_perag( spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); error = -EEXIST; - goto out_unwind; + goto out_hash_destroy; } spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); + /* first new pag is fully initialized */ + if (first_initialised == NULLAGNUMBER) + first_initialised = index; } index = xfs_set_inode_alloc(mp, agcount); @@ -239,11 +242,16 @@ xfs_initialize_perag( mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; -out_unwind: +out_hash_destroy: xfs_buf_hash_destroy(pag); +out_free_pag: kmem_free(pag); - for (; index > first_initialised; index--) { +out_unwind_new_pags: + /* unwind any prior newly initialized pags */ + for (index = first_initialised; index < agcount; index++) { pag = radix_tree_delete(&mp->m_perag_tree, index); + if (!pag) + break; xfs_buf_hash_destroy(pag); kmem_free(pag); } @@ -1073,6 +1081,13 @@ xfs_unmountfs( xfs_log_force(mp, XFS_LOG_SYNC); /* + * Wait for all busy extents to be freed, including completion of + * any discard operation. + */ + xfs_extent_busy_wait_all(mp); + flush_workqueue(xfs_discard_wq); + + /* * We now need to tell the world we are unmounting. This will allow * us to detect that the filesystem is going away and we should error * out anything that we have been retrying in the background. This will diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 7f351f706b7a..6db6fd6b82b0 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -200,11 +200,12 @@ typedef struct xfs_mount { /* * DEBUG mode instrumentation to test and/or trigger delayed allocation * block killing in the event of failed writes. When enabled, all - * buffered writes are forced to fail. All delalloc blocks in the range - * of the write (including pre-existing delalloc blocks!) are tossed as - * part of the write failure error handling sequence. + * buffered writes are silenty dropped and handled as if they failed. + * All delalloc blocks in the range of the write (including pre-existing + * delalloc blocks!) are tossed as part of the write failure error + * handling sequence. */ - bool m_fail_writes; + bool m_drop_writes; #endif } xfs_mount_t; @@ -325,13 +326,13 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) #ifdef DEBUG static inline bool -xfs_mp_fail_writes(struct xfs_mount *mp) +xfs_mp_drop_writes(struct xfs_mount *mp) { - return mp->m_fail_writes; + return mp->m_drop_writes; } #else static inline bool -xfs_mp_fail_writes(struct xfs_mount *mp) +xfs_mp_drop_writes(struct xfs_mount *mp) { return 0; } @@ -384,6 +385,8 @@ typedef struct xfs_perag { xfs_agino_t pagl_rightrec; spinlock_t pagb_lock; /* lock for pagb_tree */ struct rb_root pagb_tree; /* ordered tree of busy extents */ + unsigned int pagb_gen; /* generation count for pagb_tree */ + wait_queue_head_t pagb_wait; /* woken when pagb_gen changes */ atomic_t pagf_fstrms; /* # of filestreams active in this AG */ diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 07593a362cd0..da6d08fb359c 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -82,11 +82,22 @@ * mappings are a reservation against the free space in the filesystem; * adjacent mappings can also be combined into fewer larger mappings. * + * As an optimization, the CoW extent size hint (cowextsz) creates + * outsized aligned delalloc reservations in the hope of landing out of + * order nearby CoW writes in a single extent on disk, thereby reducing + * fragmentation and improving future performance. + * + * D: --RRRRRRSSSRRRRRRRR--- (data fork) + * C: ------DDDDDDD--------- (CoW fork) + * * When dirty pages are being written out (typically in writepage), the - * delalloc reservations are converted into real mappings by allocating - * blocks and replacing the delalloc mapping with real ones. A delalloc - * mapping can be replaced by several real ones if the free space is - * fragmented. + * delalloc reservations are converted into unwritten mappings by + * allocating blocks and replacing the delalloc mapping with real ones. + * A delalloc mapping can be replaced by several unwritten ones if the + * free space is fragmented. + * + * D: --RRRRRRSSSRRRRRRRR--- + * C: ------UUUUUUU--------- * * We want to adapt the delalloc mechanism for copy-on-write, since the * write paths are similar. The first two steps (creating the reservation @@ -101,13 +112,29 @@ * Block-aligned directio writes will use the same mechanism as buffered * writes. * + * Just prior to submitting the actual disk write requests, we convert + * the extents representing the range of the file actually being written + * (as opposed to extra pieces created for the cowextsize hint) to real + * extents. This will become important in the next step: + * + * D: --RRRRRRSSSRRRRRRRR--- + * C: ------UUrrUUU--------- + * * CoW remapping must be done after the data block write completes, * because we don't want to destroy the old data fork map until we're sure * the new block has been written. Since the new mappings are kept in a * separate fork, we can simply iterate these mappings to find the ones * that cover the file blocks that we just CoW'd. For each extent, simply * unmap the corresponding range in the data fork, map the new range into - * the data fork, and remove the extent from the CoW fork. + * the data fork, and remove the extent from the CoW fork. Because of + * the presence of the cowextsize hint, however, we must be careful + * only to remap the blocks that we've actually written out -- we must + * never remap delalloc reservations nor CoW staging blocks that have + * yet to be written. This corresponds exactly to the real extents in + * the CoW fork: + * + * D: --RRRRRRrrSRRRRRRRR--- + * C: ------UU--UUU--------- * * Since the remapping operation can be applied to an arbitrary file * range, we record the need for the remap step as a flag in the ioend @@ -296,103 +323,165 @@ xfs_reflink_reserve_cow( return 0; } -/* Allocate all CoW reservations covering a range of blocks in a file. */ -static int -__xfs_reflink_allocate_cow( - struct xfs_inode *ip, - xfs_fileoff_t *offset_fsb, - xfs_fileoff_t end_fsb) +/* Convert part of an unwritten CoW extent to a real one. */ +STATIC int +xfs_reflink_convert_cow_extent( + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + struct xfs_defer_ops *dfops) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_bmbt_irec imap; - struct xfs_defer_ops dfops; - struct xfs_trans *tp; - xfs_fsblock_t first_block; - int nimaps = 1, error; - bool shared; - - xfs_defer_init(&dfops, &first_block); + xfs_fsblock_t first_block; + int nimaps = 1; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, - XFS_TRANS_RESERVE, &tp); - if (error) - return error; + if (imap->br_state == XFS_EXT_NORM) + return 0; - xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trim_extent(imap, offset_fsb, count_fsb); + trace_xfs_reflink_convert_cow(ip, imap); + if (imap->br_blockcount == 0) + return 0; + return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount, + XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block, + 0, imap, &nimaps, dfops); +} - /* Read extent from the source file. */ - nimaps = 1; - error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, - &imap, &nimaps, 0); - if (error) - goto out_unlock; - ASSERT(nimaps == 1); +/* Convert all of the unwritten CoW extents in a file's range to real ones. */ +int +xfs_reflink_convert_cow( + struct xfs_inode *ip, + xfs_off_t offset, + xfs_off_t count) +{ + struct xfs_bmbt_irec got; + struct xfs_defer_ops dfops; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); + xfs_extnum_t idx; + bool found; + int error = 0; - error = xfs_reflink_reserve_cow(ip, &imap, &shared); - if (error) - goto out_trans_cancel; + xfs_ilock(ip, XFS_ILOCK_EXCL); - if (!shared) { - *offset_fsb = imap.br_startoff + imap.br_blockcount; - goto out_trans_cancel; + /* Convert all the extents to real from unwritten. */ + for (found = xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got); + found && got.br_startoff < end_fsb; + found = xfs_iext_get_extent(ifp, ++idx, &got)) { + error = xfs_reflink_convert_cow_extent(ip, &got, offset_fsb, + end_fsb - offset_fsb, &dfops); + if (error) + break; } - xfs_trans_ijoin(tp, ip, 0); - error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount, - XFS_BMAPI_COWFORK, &first_block, - XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), - &imap, &nimaps, &dfops); - if (error) - goto out_trans_cancel; - - error = xfs_defer_finish(&tp, &dfops, NULL); - if (error) - goto out_trans_cancel; - - error = xfs_trans_commit(tp); - - *offset_fsb = imap.br_startoff + imap.br_blockcount; -out_unlock: + /* Finish up. */ xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; -out_trans_cancel: - xfs_defer_cancel(&dfops); - xfs_trans_cancel(tp); - goto out_unlock; } -/* Allocate all CoW reservations covering a part of a file. */ +/* Allocate all CoW reservations covering a range of blocks in a file. */ int -xfs_reflink_allocate_cow_range( +xfs_reflink_allocate_cow( struct xfs_inode *ip, - xfs_off_t offset, - xfs_off_t count) + struct xfs_bmbt_irec *imap, + bool *shared, + uint *lockmode) { struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); - xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); - int error; + xfs_fileoff_t offset_fsb = imap->br_startoff; + xfs_filblks_t count_fsb = imap->br_blockcount; + struct xfs_bmbt_irec got; + struct xfs_defer_ops dfops; + struct xfs_trans *tp = NULL; + xfs_fsblock_t first_block; + int nimaps, error = 0; + bool trimmed; + xfs_filblks_t resaligned; + xfs_extlen_t resblks = 0; + xfs_extnum_t idx; +retry: ASSERT(xfs_is_reflink_inode(ip)); - - trace_xfs_reflink_allocate_cow_range(ip, offset, count); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); /* - * Make sure that the dquots are there. + * Even if the extent is not shared we might have a preallocation for + * it in the COW fork. If so use it. */ - error = xfs_qm_dqattach(ip, 0); - if (error) - return error; + if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &idx, &got) && + got.br_startoff <= offset_fsb) { + *shared = true; - while (offset_fsb < end_fsb) { - error = __xfs_reflink_allocate_cow(ip, &offset_fsb, end_fsb); - if (error) { - trace_xfs_reflink_allocate_cow_range_error(ip, error, - _RET_IP_); - break; + /* If we have a real allocation in the COW fork we're done. */ + if (!isnullstartblock(got.br_startblock)) { + xfs_trim_extent(&got, offset_fsb, count_fsb); + *imap = got; + goto convert; } + + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); + } else { + error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); + if (error || !*shared) + goto out; + } + + if (!tp) { + resaligned = xfs_aligned_fsb_count(imap->br_startoff, + imap->br_blockcount, xfs_get_cowextsz_hint(ip)); + resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + + xfs_iunlock(ip, *lockmode); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); + *lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, *lockmode); + + if (error) + return error; + + error = xfs_qm_dqattach_locked(ip, 0); + if (error) + goto out; + goto retry; } + error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, + XFS_QMOPT_RES_REGBLKS); + if (error) + goto out; + + xfs_trans_ijoin(tp, ip, 0); + + xfs_defer_init(&dfops, &first_block); + nimaps = 1; + + /* Allocate the entire reservation as unwritten blocks. */ + error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, + XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block, + resblks, imap, &nimaps, &dfops); + if (error) + goto out_bmap_cancel; + + /* Finish up. */ + error = xfs_defer_finish(&tp, &dfops, NULL); + if (error) + goto out_bmap_cancel; + + error = xfs_trans_commit(tp); + if (error) + return error; +convert: + return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb, + &dfops); +out_bmap_cancel: + xfs_defer_cancel(&dfops); + xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0, + XFS_QMOPT_RES_REGBLKS); +out: + if (tp) + xfs_trans_cancel(tp); return error; } @@ -641,6 +730,16 @@ xfs_reflink_end_cow( ASSERT(!isnullstartblock(got.br_startblock)); + /* + * Don't remap unwritten extents; these are + * speculatively preallocated CoW extents that have been + * allocated but have not yet been involved in a write. + */ + if (got.br_state == XFS_EXT_UNWRITTEN) { + idx--; + goto next_extent; + } + /* Unmap the old blocks in the data fork. */ xfs_defer_init(&dfops, &firstfsb); rlen = del.br_blockcount; @@ -855,13 +954,14 @@ STATIC int xfs_reflink_update_dest( struct xfs_inode *dest, xfs_off_t newlen, - xfs_extlen_t cowextsize) + xfs_extlen_t cowextsize, + bool is_dedupe) { struct xfs_mount *mp = dest->i_mount; struct xfs_trans *tp; int error; - if (newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) + if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) return 0; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); @@ -882,6 +982,10 @@ xfs_reflink_update_dest( dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; } + if (!is_dedupe) { + xfs_trans_ichgtime(tp, dest, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + } xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE); error = xfs_trans_commit(tp); @@ -1195,7 +1299,8 @@ xfs_reflink_remap_range( !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) cowextsize = src->i_d.di_cowextsize; - ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize); + ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, + is_dedupe); out_unlock: xfs_iunlock(src, XFS_MMAPLOCK_EXCL); diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index aa6a4d64bd35..33ac9b8db683 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -28,8 +28,10 @@ extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, bool *shared); -extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, - xfs_off_t offset, xfs_off_t count); +extern int xfs_reflink_allocate_cow(struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode); +extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset, + xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, struct xfs_bmbt_irec *imap); extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 802bcc326d9f..c57aa7f18087 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1093,7 +1093,6 @@ xfs_rtallocate_extent( xfs_extlen_t minlen, /* minimum length to allocate */ xfs_extlen_t maxlen, /* maximum length to allocate */ xfs_extlen_t *len, /* out: actual length allocated */ - xfs_alloctype_t type, /* allocation type XFS_ALLOCTYPE... */ int wasdel, /* was a delayed allocation extent */ xfs_extlen_t prod, /* extent product factor */ xfs_rtblock_t *rtblock) /* out: start block allocated */ @@ -1123,27 +1122,16 @@ xfs_rtallocate_extent( } } +retry: sumbp = NULL; - /* - * Allocate by size, or near another block, or exactly at some block. - */ - switch (type) { - case XFS_ALLOCTYPE_ANY_AG: + if (bno == 0) { error = xfs_rtallocate_extent_size(mp, tp, minlen, maxlen, len, &sumbp, &sb, prod, &r); - break; - case XFS_ALLOCTYPE_NEAR_BNO: + } else { error = xfs_rtallocate_extent_near(mp, tp, bno, minlen, maxlen, len, &sumbp, &sb, prod, &r); - break; - case XFS_ALLOCTYPE_THIS_BNO: - error = xfs_rtallocate_extent_exact(mp, tp, bno, minlen, maxlen, - len, &sumbp, &sb, prod, &r); - break; - default: - error = -EIO; - ASSERT(0); } + if (error) return error; @@ -1158,7 +1146,11 @@ xfs_rtallocate_extent( xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FREXTENTS, -slen); else xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, -slen); + } else if (prod > 1) { + prod = 1; + goto retry; } + *rtblock = r; return 0; } diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index 355dd9e1cb64..51dd3c726608 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -40,7 +40,6 @@ xfs_rtallocate_extent( xfs_extlen_t minlen, /* minimum length to allocate */ xfs_extlen_t maxlen, /* maximum length to allocate */ xfs_extlen_t *len, /* out: actual length allocated */ - xfs_alloctype_t type, /* allocation type XFS_ALLOCTYPE... */ int wasdel, /* was a delayed allocation extent */ xfs_extlen_t prod, /* extent product factor */ xfs_rtblock_t *rtblock); /* out: start block allocated */ @@ -122,7 +121,7 @@ int xfs_rtfree_range(struct xfs_mount *mp, struct xfs_trans *tp, #else -# define xfs_rtallocate_extent(t,b,min,max,l,a,f,p,rb) (ENOSYS) +# define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb) (ENOSYS) # define xfs_rtfree_extent(t,b,l) (ENOSYS) # define xfs_rtpick_extent(m,t,l,rb) (ENOSYS) # define xfs_growfs_rt(mp,in) (ENOSYS) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index eecbaac08eba..890862f2447c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1956,12 +1956,20 @@ xfs_init_workqueues(void) if (!xfs_alloc_wq) return -ENOMEM; + xfs_discard_wq = alloc_workqueue("xfsdiscard", WQ_UNBOUND, 0); + if (!xfs_discard_wq) + goto out_free_alloc_wq; + return 0; +out_free_alloc_wq: + destroy_workqueue(xfs_alloc_wq); + return -ENOMEM; } STATIC void xfs_destroy_workqueues(void) { + destroy_workqueue(xfs_discard_wq); destroy_workqueue(xfs_alloc_wq); } diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index b6418abd85ad..5f2f32408011 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -73,6 +73,8 @@ extern const struct quotactl_ops xfs_quotactl_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); +extern struct workqueue_struct *xfs_discard_wq; + #define XFS_M(sb) ((struct xfs_mount *)((sb)->s_fs_info)) #endif /* __XFS_SUPER_H__ */ diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index de6195e38910..80ac15fb9638 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -93,7 +93,7 @@ to_mp(struct kobject *kobject) #ifdef DEBUG STATIC ssize_t -fail_writes_store( +drop_writes_store( struct kobject *kobject, const char *buf, size_t count) @@ -107,9 +107,9 @@ fail_writes_store( return ret; if (val == 1) - mp->m_fail_writes = true; + mp->m_drop_writes = true; else if (val == 0) - mp->m_fail_writes = false; + mp->m_drop_writes = false; else return -EINVAL; @@ -117,21 +117,21 @@ fail_writes_store( } STATIC ssize_t -fail_writes_show( +drop_writes_show( struct kobject *kobject, char *buf) { struct xfs_mount *mp = to_mp(kobject); - return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_writes ? 1 : 0); + return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_drop_writes ? 1 : 0); } -XFS_SYSFS_ATTR_RW(fail_writes); +XFS_SYSFS_ATTR_RW(drop_writes); #endif /* DEBUG */ static struct attribute *xfs_mp_attrs[] = { #ifdef DEBUG - ATTR_LIST(fail_writes), + ATTR_LIST(drop_writes), #endif NULL, }; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 69c5bcd9a51b..fb7555e73a62 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2245,7 +2245,6 @@ DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range); /* deferred ops */ struct xfs_defer_pending; -struct xfs_defer_intake; struct xfs_defer_ops; DECLARE_EVENT_CLASS(xfs_defer_class, @@ -3089,6 +3088,7 @@ DECLARE_EVENT_CLASS(xfs_inode_irec_class, __field(xfs_fileoff_t, lblk) __field(xfs_extlen_t, len) __field(xfs_fsblock_t, pblk) + __field(int, state) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; @@ -3096,13 +3096,15 @@ DECLARE_EVENT_CLASS(xfs_inode_irec_class, __entry->lblk = irec->br_startoff; __entry->len = irec->br_blockcount; __entry->pblk = irec->br_startblock; + __entry->state = irec->br_state; ), - TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x pblk %llu", + TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x pblk %llu st %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, - __entry->pblk) + __entry->pblk, + __entry->state) ); #define DEFINE_INODE_IREC_EVENT(name) \ DEFINE_EVENT(xfs_inode_irec_class, name, \ @@ -3242,11 +3244,11 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_around_shared); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); +DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow); DEFINE_RW_EVENT(xfs_reflink_reserve_cow); -DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range); -DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write); +DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write); DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping); DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec); @@ -3254,7 +3256,6 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap); -DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 61b7fbdd3ebd..1646f659b60f 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -32,7 +32,6 @@ struct xfs_mount; struct xfs_trans; struct xfs_trans_res; struct xfs_dquot_acct; -struct xfs_busy_extent; struct xfs_rud_log_item; struct xfs_rui_log_item; struct xfs_btree_cur; |