diff options
Diffstat (limited to 'fs')
74 files changed, 2768 insertions, 1630 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 7ab616601141..6f4678d98df7 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -159,8 +159,6 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, if (!PagePrivate(page)) return; - ClearPageChecked(page); - dout("%p invalidatepage %p idx %lu full dirty page\n", inode, page, page->index); @@ -183,6 +181,47 @@ static int ceph_releasepage(struct page *page, gfp_t g) } /* + * Read some contiguous pages. If we cross a stripe boundary, shorten + * *plen. Return number of bytes read, or error. + */ +static int ceph_sync_readpages(struct ceph_fs_client *fsc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + u64 off, u64 *plen, + u32 truncate_seq, u64 truncate_size, + struct page **pages, int num_pages, + int page_align) +{ + struct ceph_osd_client *osdc = &fsc->client->osdc; + struct ceph_osd_request *req; + int rc = 0; + + dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino, + vino.snap, off, *plen); + req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1, + CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, + NULL, truncate_seq, truncate_size, + false); + if (IS_ERR(req)) + return PTR_ERR(req); + + /* it may be a short read due to an object boundary */ + osd_req_op_extent_osd_data_pages(req, 0, + pages, *plen, page_align, false, false); + + dout("readpages final extent is %llu~%llu (%llu bytes align %d)\n", + off, *plen, *plen, page_align); + + rc = ceph_osdc_start_request(osdc, req, false); + if (!rc) + rc = ceph_osdc_wait_request(osdc, req); + + ceph_osdc_put_request(req); + dout("readpages result %d\n", rc); + return rc; +} + +/* * read a single page, without unlocking it. */ static int ceph_do_readpage(struct file *filp, struct page *page) @@ -218,7 +257,7 @@ static int ceph_do_readpage(struct file *filp, struct page *page) dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); - err = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode), + err = ceph_sync_readpages(fsc, ceph_vino(inode), &ci->i_layout, off, &len, ci->i_truncate_seq, ci->i_truncate_size, &page, 1, 0); @@ -571,6 +610,47 @@ static u64 get_writepages_data_length(struct inode *inode, } /* + * do a synchronous write on N pages + */ +static int ceph_sync_writepages(struct ceph_fs_client *fsc, + struct ceph_vino vino, + struct ceph_file_layout *layout, + struct ceph_snap_context *snapc, + u64 off, u64 len, + u32 truncate_seq, u64 truncate_size, + struct timespec64 *mtime, + struct page **pages, int num_pages) +{ + struct ceph_osd_client *osdc = &fsc->client->osdc; + struct ceph_osd_request *req; + int rc = 0; + int page_align = off & ~PAGE_MASK; + + req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1, + CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, + snapc, truncate_seq, truncate_size, + true); + if (IS_ERR(req)) + return PTR_ERR(req); + + /* it may be a short write due to an object boundary */ + osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align, + false, false); + dout("writepages %llu~%llu (%llu bytes)\n", off, len, len); + + req->r_mtime = *mtime; + rc = ceph_osdc_start_request(osdc, req, true); + if (!rc) + rc = ceph_osdc_wait_request(osdc, req); + + ceph_osdc_put_request(req); + if (rc == 0) + rc = len; + dout("writepages result %d\n", rc); + return rc; +} + +/* * Write a single page, but leave the page locked. * * If we get a write error, mark the mapping for error, but still adjust the @@ -628,7 +708,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); set_page_writeback(page); - err = ceph_osdc_writepages(&fsc->client->osdc, ceph_vino(inode), + err = ceph_sync_writepages(fsc, ceph_vino(inode), &ci->i_layout, snapc, page_off, len, ceph_wbc.truncate_seq, ceph_wbc.truncate_size, @@ -1575,7 +1655,7 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf) do { lock_page(page); - if ((off > size) || (page->mapping != inode->i_mapping)) { + if (page_mkwrite_check_truncate(page, inode) < 0) { unlock_page(page); ret = VM_FAULT_NOPAGE; break; diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 270b769607a2..2f5cb6bc78e1 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -32,7 +32,7 @@ struct ceph_fscache_entry { size_t uniq_len; /* The following members must be last */ struct ceph_fsid fsid; - char uniquifier[0]; + char uniquifier[]; }; static const struct fscache_cookie_def ceph_fscache_fsid_object_def = { diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 28ae0c134700..185db76300b3 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -490,13 +490,10 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc, struct ceph_inode_info *ci) { struct ceph_mount_options *opt = mdsc->fsc->mount_options; - - ci->i_hold_caps_min = round_jiffies(jiffies + - opt->caps_wanted_delay_min * HZ); ci->i_hold_caps_max = round_jiffies(jiffies + opt->caps_wanted_delay_max * HZ); - dout("__cap_set_timeouts %p min %lu max %lu\n", &ci->vfs_inode, - ci->i_hold_caps_min - jiffies, ci->i_hold_caps_max - jiffies); + dout("__cap_set_timeouts %p %lu\n", &ci->vfs_inode, + ci->i_hold_caps_max - jiffies); } /* @@ -508,10 +505,9 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc, * -> we take mdsc->cap_delay_lock */ static void __cap_delay_requeue(struct ceph_mds_client *mdsc, - struct ceph_inode_info *ci, - bool set_timeout) + struct ceph_inode_info *ci) { - dout("__cap_delay_requeue %p flags %d at %lu\n", &ci->vfs_inode, + dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->vfs_inode, ci->i_ceph_flags, ci->i_hold_caps_max); if (!mdsc->stopping) { spin_lock(&mdsc->cap_delay_lock); @@ -520,8 +516,7 @@ static void __cap_delay_requeue(struct ceph_mds_client *mdsc, goto no_change; list_del_init(&ci->i_cap_delay_list); } - if (set_timeout) - __cap_set_timeouts(mdsc, ci); + __cap_set_timeouts(mdsc, ci); list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_delay_list); no_change: spin_unlock(&mdsc->cap_delay_lock); @@ -561,19 +556,20 @@ static void __cap_delay_cancel(struct ceph_mds_client *mdsc, spin_unlock(&mdsc->cap_delay_lock); } -/* - * Common issue checks for add_cap, handle_cap_grant. - */ +/* Common issue checks for add_cap, handle_cap_grant. */ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, unsigned issued) { unsigned had = __ceph_caps_issued(ci, NULL); + lockdep_assert_held(&ci->i_ceph_lock); + /* * Each time we receive FILE_CACHE anew, we increment * i_rdcache_gen. */ - if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) && + if (S_ISREG(ci->vfs_inode.i_mode) && + (issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) && (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) { ci->i_rdcache_gen++; } @@ -592,6 +588,13 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, __ceph_dir_clear_complete(ci); } } + + /* Wipe saved layout if we're losing DIR_CREATE caps */ + if (S_ISDIR(ci->vfs_inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) && + !(issued & CEPH_CAP_DIR_CREATE)) { + ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns)); + memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout)); + } } /* @@ -605,7 +608,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, */ void ceph_add_cap(struct inode *inode, struct ceph_mds_session *session, u64 cap_id, - int fmode, unsigned issued, unsigned wanted, + unsigned issued, unsigned wanted, unsigned seq, unsigned mseq, u64 realmino, int flags, struct ceph_cap **new_cap) { @@ -621,13 +624,6 @@ void ceph_add_cap(struct inode *inode, dout("add_cap %p mds%d cap %llx %s seq %d\n", inode, session->s_mds, cap_id, ceph_cap_string(issued), seq); - /* - * If we are opening the file, include file mode wanted bits - * in wanted. - */ - if (fmode >= 0) - wanted |= ceph_caps_for_mode(fmode); - spin_lock(&session->s_gen_ttl_lock); gen = session->s_cap_gen; spin_unlock(&session->s_gen_ttl_lock); @@ -725,7 +721,7 @@ void ceph_add_cap(struct inode *inode, dout(" issued %s, mds wanted %s, actual %s, queueing\n", ceph_cap_string(issued), ceph_cap_string(wanted), ceph_cap_string(actual_wanted)); - __cap_delay_requeue(mdsc, ci, true); + __cap_delay_requeue(mdsc, ci); } if (flags & CEPH_CAP_FLAG_AUTH) { @@ -752,9 +748,6 @@ void ceph_add_cap(struct inode *inode, cap->issue_seq = seq; cap->mseq = mseq; cap->cap_gen = gen; - - if (fmode >= 0) - __ceph_get_fmode(ci, fmode); } /* @@ -958,29 +951,97 @@ int __ceph_caps_used(struct ceph_inode_info *ci) if (ci->i_rd_ref) used |= CEPH_CAP_FILE_RD; if (ci->i_rdcache_ref || - (!S_ISDIR(ci->vfs_inode.i_mode) && /* ignore readdir cache */ + (S_ISREG(ci->vfs_inode.i_mode) && ci->vfs_inode.i_data.nrpages)) used |= CEPH_CAP_FILE_CACHE; if (ci->i_wr_ref) used |= CEPH_CAP_FILE_WR; if (ci->i_wb_ref || ci->i_wrbuffer_ref) used |= CEPH_CAP_FILE_BUFFER; + if (ci->i_fx_ref) + used |= CEPH_CAP_FILE_EXCL; return used; } +#define FMODE_WAIT_BIAS 1000 + /* * wanted, by virtue of open file modes */ int __ceph_caps_file_wanted(struct ceph_inode_info *ci) { - int i, bits = 0; - for (i = 0; i < CEPH_FILE_MODE_BITS; i++) { - if (ci->i_nr_by_mode[i]) - bits |= 1 << i; + const int PIN_SHIFT = ffs(CEPH_FILE_MODE_PIN); + const int RD_SHIFT = ffs(CEPH_FILE_MODE_RD); + const int WR_SHIFT = ffs(CEPH_FILE_MODE_WR); + const int LAZY_SHIFT = ffs(CEPH_FILE_MODE_LAZY); + struct ceph_mount_options *opt = + ceph_inode_to_client(&ci->vfs_inode)->mount_options; + unsigned long used_cutoff = jiffies - opt->caps_wanted_delay_max * HZ; + unsigned long idle_cutoff = jiffies - opt->caps_wanted_delay_min * HZ; + + if (S_ISDIR(ci->vfs_inode.i_mode)) { + int want = 0; + + /* use used_cutoff here, to keep dir's wanted caps longer */ + if (ci->i_nr_by_mode[RD_SHIFT] > 0 || + time_after(ci->i_last_rd, used_cutoff)) + want |= CEPH_CAP_ANY_SHARED; + + if (ci->i_nr_by_mode[WR_SHIFT] > 0 || + time_after(ci->i_last_wr, used_cutoff)) { + want |= CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL; + if (opt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) + want |= CEPH_CAP_ANY_DIR_OPS; + } + + if (want || ci->i_nr_by_mode[PIN_SHIFT] > 0) + want |= CEPH_CAP_PIN; + + return want; + } else { + int bits = 0; + + if (ci->i_nr_by_mode[RD_SHIFT] > 0) { + if (ci->i_nr_by_mode[RD_SHIFT] >= FMODE_WAIT_BIAS || + time_after(ci->i_last_rd, used_cutoff)) + bits |= 1 << RD_SHIFT; + } else if (time_after(ci->i_last_rd, idle_cutoff)) { + bits |= 1 << RD_SHIFT; + } + + if (ci->i_nr_by_mode[WR_SHIFT] > 0) { + if (ci->i_nr_by_mode[WR_SHIFT] >= FMODE_WAIT_BIAS || + time_after(ci->i_last_wr, used_cutoff)) + bits |= 1 << WR_SHIFT; + } else if (time_after(ci->i_last_wr, idle_cutoff)) { + bits |= 1 << WR_SHIFT; + } + + /* check lazyio only when read/write is wanted */ + if ((bits & (CEPH_FILE_MODE_RDWR << 1)) && + ci->i_nr_by_mode[LAZY_SHIFT] > 0) + bits |= 1 << LAZY_SHIFT; + + return bits ? ceph_caps_for_mode(bits >> 1) : 0; } - if (bits == 0) - return 0; - return ceph_caps_for_mode(bits >> 1); +} + +/* + * wanted, by virtue of open file modes AND cap refs (buffered/cached data) + */ +int __ceph_caps_wanted(struct ceph_inode_info *ci) +{ + int w = __ceph_caps_file_wanted(ci) | __ceph_caps_used(ci); + if (S_ISDIR(ci->vfs_inode.i_mode)) { + /* we want EXCL if holding caps of dir ops */ + if (w & CEPH_CAP_ANY_DIR_OPS) + w |= CEPH_CAP_FILE_EXCL; + } else { + /* we want EXCL if dirty data */ + if (w & CEPH_CAP_FILE_BUFFER) + w |= CEPH_CAP_FILE_EXCL; + } + return w; } /* @@ -1004,14 +1065,6 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check) return mds_wanted; } -/* - * called under i_ceph_lock - */ -static int __ceph_is_single_caps(struct ceph_inode_info *ci) -{ - return rb_first(&ci->i_caps) == rb_last(&ci->i_caps); -} - int ceph_is_any_caps(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); @@ -1274,9 +1327,15 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, struct cap_msg_args arg; int held, revoking; int wake = 0; - int delayed = 0; int ret; + /* Don't send anything if it's still being created. Return delayed */ + if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { + spin_unlock(&ci->i_ceph_lock); + dout("%s async create in flight for %p\n", __func__, inode); + return 1; + } + held = cap->issued | cap->implemented; revoking = cap->implemented & ~cap->issued; retain &= ~revoking; @@ -1287,28 +1346,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, ceph_cap_string(revoking)); BUG_ON((retain & CEPH_CAP_PIN) == 0); - arg.session = cap->session; - - /* don't release wanted unless we've waited a bit. */ - if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 && - time_before(jiffies, ci->i_hold_caps_min)) { - dout(" delaying issued %s -> %s, wanted %s -> %s on send\n", - ceph_cap_string(cap->issued), - ceph_cap_string(cap->issued & retain), - ceph_cap_string(cap->mds_wanted), - ceph_cap_string(want)); - want |= cap->mds_wanted; - retain |= cap->issued; - delayed = 1; - } - ci->i_ceph_flags &= ~(CEPH_I_NODELAY | CEPH_I_FLUSH); - if (want & ~cap->mds_wanted) { - /* user space may open/close single file frequently. - * This avoids droping mds_wanted immediately after - * requesting new mds_wanted. - */ - __cap_set_timeouts(mdsc, ci); - } + ci->i_ceph_flags &= ~CEPH_I_FLUSH; cap->issued &= retain; /* drop bits we don't want */ if (cap->implemented & ~cap->issued) { @@ -1323,6 +1361,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, cap->implemented &= cap->issued | used; cap->mds_wanted = want; + arg.session = cap->session; arg.ino = ceph_vino(inode).ino; arg.cid = cap->cap_id; arg.follows = flushing ? ci->i_head_snapc->seq : 0; @@ -1332,7 +1371,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, arg.size = inode->i_size; ci->i_reported_size = arg.size; arg.max_size = ci->i_wanted_max_size; - ci->i_requested_max_size = arg.max_size; + if (cap == ci->i_auth_cap) + ci->i_requested_max_size = arg.max_size; if (flushing & CEPH_CAP_XATTR_EXCL) { old_blob = __ceph_build_xattrs_blob(ci); @@ -1383,14 +1423,19 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, ret = send_cap_msg(&arg); if (ret < 0) { - dout("error sending cap msg, must requeue %p\n", inode); - delayed = 1; + pr_err("error sending cap msg, ino (%llx.%llx) " + "flushing %s tid %llu, requeue\n", + ceph_vinop(inode), ceph_cap_string(flushing), + flush_tid); + spin_lock(&ci->i_ceph_lock); + __cap_delay_requeue(mdsc, ci); + spin_unlock(&ci->i_ceph_lock); } if (wake) wake_up_all(&ci->i_cap_wq); - return delayed; + return ret; } static inline int __send_flush_snap(struct inode *inode, @@ -1617,6 +1662,8 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask, int was = ci->i_dirty_caps; int dirty = 0; + lockdep_assert_held(&ci->i_ceph_lock); + if (!ci->i_auth_cap) { pr_warn("__mark_dirty_caps %p %llx mask %s, " "but no auth cap (session was closed?)\n", @@ -1654,7 +1701,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask, if (((was | ci->i_flushing_caps) & CEPH_CAP_FILE_BUFFER) && (mask & CEPH_CAP_FILE_BUFFER)) dirty |= I_DIRTY_DATASYNC; - __cap_delay_requeue(mdsc, ci, true); + __cap_delay_requeue(mdsc, ci); return dirty; } @@ -1726,6 +1773,7 @@ static u64 __mark_caps_flushing(struct inode *inode, struct ceph_cap_flush *cf = NULL; int flushing; + lockdep_assert_held(&ci->i_ceph_lock); BUG_ON(ci->i_dirty_caps == 0); BUG_ON(list_empty(&ci->i_dirty_item)); BUG_ON(!ci->i_prealloc_cap_flush); @@ -1805,8 +1853,6 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci) * versus held caps. Release, flush, ack revoked caps to mds as * appropriate. * - * CHECK_CAPS_NODELAY - caller is delayed work and we should not delay - * cap release further. * CHECK_CAPS_AUTHONLY - we should only check the auth cap * CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without * further delay. @@ -1825,24 +1871,13 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags, int mds = -1; /* keep track of how far we've gone through i_caps list to avoid an infinite loop on retry */ struct rb_node *p; - int delayed = 0, sent = 0; - bool no_delay = flags & CHECK_CAPS_NODELAY; bool queue_invalidate = false; bool tried_invalidate = false; - /* if we are unmounting, flush any unused caps immediately. */ - if (mdsc->stopping) - no_delay = true; - spin_lock(&ci->i_ceph_lock); - if (ci->i_ceph_flags & CEPH_I_FLUSH) flags |= CHECK_CAPS_FLUSH; - if (!(flags & CHECK_CAPS_AUTHONLY) || - (ci->i_auth_cap && __ceph_is_single_caps(ci))) - __cap_delay_cancel(mdsc, ci); - goto retry_locked; retry: spin_lock(&ci->i_ceph_lock); @@ -1866,10 +1901,11 @@ retry_locked: * revoking the shared cap on every create/unlink * operation. */ - if (IS_RDONLY(inode)) + if (IS_RDONLY(inode)) { want = CEPH_CAP_ANY_SHARED; - else - want = CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL; + } else { + want |= CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL; + } retain |= want; } else { @@ -1885,14 +1921,13 @@ retry_locked: } dout("check_caps %p file_want %s used %s dirty %s flushing %s" - " issued %s revoking %s retain %s %s%s%s\n", inode, + " issued %s revoking %s retain %s %s%s\n", inode, ceph_cap_string(file_wanted), ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps), ceph_cap_string(ci->i_flushing_caps), ceph_cap_string(issued), ceph_cap_string(revoking), ceph_cap_string(retain), (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "", - (flags & CHECK_CAPS_NODELAY) ? " NODELAY" : "", (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : ""); /* @@ -1900,8 +1935,8 @@ retry_locked: * have cached pages, but don't want them, then try to invalidate. * If we fail, it's because pages are locked.... try again later. */ - if ((!no_delay || mdsc->stopping) && - !S_ISDIR(inode->i_mode) && /* ignore readdir cache */ + if ((!(flags & CHECK_CAPS_NOINVAL) || mdsc->stopping) && + S_ISREG(inode->i_mode) && !(ci->i_wb_ref || ci->i_wrbuffer_ref) && /* no dirty pages... */ inode->i_data.nrpages && /* have cached pages */ (revoking & (CEPH_CAP_FILE_CACHE| @@ -1973,28 +2008,17 @@ retry_locked: } /* want more caps from mds? */ - if (want & ~(cap->mds_wanted | cap->issued)) - goto ack; + if (want & ~cap->mds_wanted) { + if (want & ~(cap->mds_wanted | cap->issued)) + goto ack; + if (!__cap_is_valid(cap)) + goto ack; + } /* things we might delay */ if ((cap->issued & ~retain) == 0) continue; /* nope, all good */ - if (no_delay) - goto ack; - - /* delay? */ - if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 && - time_before(jiffies, ci->i_hold_caps_max)) { - dout(" delaying issued %s -> %s, wanted %s -> %s\n", - ceph_cap_string(cap->issued), - ceph_cap_string(cap->issued & retain), - ceph_cap_string(cap->mds_wanted), - ceph_cap_string(want)); - delayed++; - continue; - } - ack: if (session && session != cap->session) { dout("oops, wrong session %p mutex\n", session); @@ -2055,18 +2079,20 @@ ack: } mds = cap->mds; /* remember mds, so we don't repeat */ - sent++; /* __send_cap drops i_ceph_lock */ - delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0, - cap_used, want, retain, flushing, - flush_tid, oldest_flush_tid); + __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0, cap_used, want, + retain, flushing, flush_tid, oldest_flush_tid); goto retry; /* retake i_ceph_lock and restart our cap scan. */ } - /* Reschedule delayed caps release if we delayed anything */ - if (delayed) - __cap_delay_requeue(mdsc, ci, false); + /* periodically re-calculate caps wanted by open files */ + if (__ceph_is_any_real_caps(ci) && + list_empty(&ci->i_cap_delay_list) && + (file_wanted & ~CEPH_CAP_PIN) && + !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) { + __cap_delay_requeue(mdsc, ci); + } spin_unlock(&ci->i_ceph_lock); @@ -2095,7 +2121,6 @@ retry: retry_locked: if (ci->i_dirty_caps && ci->i_auth_cap) { struct ceph_cap *cap = ci->i_auth_cap; - int delayed; if (session != cap->session) { spin_unlock(&ci->i_ceph_lock); @@ -2124,18 +2149,10 @@ retry_locked: &oldest_flush_tid); /* __send_cap drops i_ceph_lock */ - delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, - CEPH_CLIENT_CAPS_SYNC, - __ceph_caps_used(ci), - __ceph_caps_wanted(ci), - (cap->issued | cap->implemented), - flushing, flush_tid, oldest_flush_tid); - - if (delayed) { - spin_lock(&ci->i_ceph_lock); - __cap_delay_requeue(mdsc, ci, true); - spin_unlock(&ci->i_ceph_lock); - } + __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, CEPH_CLIENT_CAPS_SYNC, + __ceph_caps_used(ci), __ceph_caps_wanted(ci), + (cap->issued | cap->implemented), + flushing, flush_tid, oldest_flush_tid); } else { if (!list_empty(&ci->i_cap_flush_list)) { struct ceph_cap_flush *cf = @@ -2233,6 +2250,10 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) if (datasync) goto out; + ret = ceph_wait_on_async_create(inode); + if (ret) + goto out; + dirty = try_flush_caps(inode, &flush_tid); dout("fsync dirty caps are %s\n", ceph_cap_string(dirty)); @@ -2335,22 +2356,13 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, if (cf->caps) { dout("kick_flushing_caps %p cap %p tid %llu %s\n", inode, cap, cf->tid, ceph_cap_string(cf->caps)); - ci->i_ceph_flags |= CEPH_I_NODELAY; - - ret = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, + __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, (cf->tid < last_snap_flush ? CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0), __ceph_caps_used(ci), __ceph_caps_wanted(ci), (cap->issued | cap->implemented), cf->caps, cf->tid, oldest_flush_tid); - if (ret) { - pr_err("kick_flushing_caps: error sending " - "cap flush, ino (%llx.%llx) " - "tid %llu flushing %s\n", - ceph_vinop(inode), cf->tid, - ceph_cap_string(cf->caps)); - } } else { struct ceph_cap_snap *capsnap = container_of(cf, struct ceph_cap_snap, @@ -2457,16 +2469,15 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, } } -static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session, - struct inode *inode) - __releases(ci->i_ceph_lock) +void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session, + struct ceph_inode_info *ci) { - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_cap *cap; + struct ceph_mds_client *mdsc = session->s_mdsc; + struct ceph_cap *cap = ci->i_auth_cap; + + lockdep_assert_held(&ci->i_ceph_lock); - cap = ci->i_auth_cap; - dout("kick_flushing_inode_caps %p flushing %s\n", inode, + dout("%s %p flushing %s\n", __func__, &ci->vfs_inode, ceph_cap_string(ci->i_flushing_caps)); if (!list_empty(&ci->i_cap_flush_list)) { @@ -2478,9 +2489,6 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc, spin_unlock(&mdsc->cap_dirty_lock); __kick_flushing_caps(mdsc, session, ci, oldest_flush_tid); - spin_unlock(&ci->i_ceph_lock); - } else { - spin_unlock(&ci->i_ceph_lock); } } @@ -2488,18 +2496,20 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc, /* * Take references to capabilities we hold, so that we don't release * them to the MDS prematurely. - * - * Protected by i_ceph_lock. */ -static void __take_cap_refs(struct ceph_inode_info *ci, int got, +void ceph_take_cap_refs(struct ceph_inode_info *ci, int got, bool snap_rwsem_locked) { + lockdep_assert_held(&ci->i_ceph_lock); + if (got & CEPH_CAP_PIN) ci->i_pin_ref++; if (got & CEPH_CAP_FILE_RD) ci->i_rd_ref++; if (got & CEPH_CAP_FILE_CACHE) ci->i_rdcache_ref++; + if (got & CEPH_CAP_FILE_EXCL) + ci->i_fx_ref++; if (got & CEPH_CAP_FILE_WR) { if (ci->i_wr_ref == 0 && !ci->i_head_snapc) { BUG_ON(!snap_rwsem_locked); @@ -2512,7 +2522,7 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got, if (ci->i_wb_ref == 0) ihold(&ci->vfs_inode); ci->i_wb_ref++; - dout("__take_cap_refs %p wb %d -> %d (?)\n", + dout("%s %p wb %d -> %d (?)\n", __func__, &ci->vfs_inode, ci->i_wb_ref-1, ci->i_wb_ref); } } @@ -2524,14 +2534,16 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got, * Note that caller is responsible for ensuring max_size increases are * requested from the MDS. * - * Returns 0 if caps were not able to be acquired (yet), a 1 if they were, - * or a negative error code. - * - * FIXME: how does a 0 return differ from -EAGAIN? + * Returns 0 if caps were not able to be acquired (yet), 1 if succeed, + * or a negative error code. There are 3 speical error codes: + * -EAGAIN: need to sleep but non-blocking is specified + * -EFBIG: ask caller to call check_max_size() and try again. + * -ESTALE: ask caller to call ceph_renew_caps() and try again. */ enum { - NON_BLOCKING = 1, - CHECK_FILELOCK = 2, + /* first 8 bits are reserved for CEPH_FILE_MODE_FOO */ + NON_BLOCKING = (1 << 8), + CHECK_FILELOCK = (1 << 9), }; static int try_get_cap_refs(struct inode *inode, int need, int want, @@ -2541,7 +2553,6 @@ static int try_get_cap_refs(struct inode *inode, int need, int want, struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; int ret = 0; int have, implemented; - int file_wanted; bool snap_rwsem_locked = false; dout("get_cap_refs %p need %s want %s\n", inode, @@ -2557,15 +2568,6 @@ again: goto out_unlock; } - /* make sure file is actually open */ - file_wanted = __ceph_caps_file_wanted(ci); - if ((file_wanted & need) != need) { - dout("try_get_cap_refs need %s file_wanted %s, EBADF\n", - ceph_cap_string(need), ceph_cap_string(file_wanted)); - ret = -EBADF; - goto out_unlock; - } - /* finish pending truncate */ while (ci->i_truncate_pending) { spin_unlock(&ci->i_ceph_lock); @@ -2584,7 +2586,7 @@ again: dout("get_cap_refs %p endoff %llu > maxsize %llu\n", inode, endoff, ci->i_max_size); if (endoff > ci->i_requested_max_size) - ret = -EAGAIN; + ret = ci->i_auth_cap ? -EFBIG : -ESTALE; goto out_unlock; } /* @@ -2630,51 +2632,55 @@ again: } snap_rwsem_locked = true; } - *got = need | (have & want); - if ((need & CEPH_CAP_FILE_RD) && + if ((have & want) == want) + *got = need | want; + else + *got = need; + if (S_ISREG(inode->i_mode) && + (need & CEPH_CAP_FILE_RD) && !(*got & CEPH_CAP_FILE_CACHE)) ceph_disable_fscache_readpage(ci); - __take_cap_refs(ci, *got, true); + ceph_take_cap_refs(ci, *got, true); ret = 1; } } else { int session_readonly = false; - if ((need & CEPH_CAP_FILE_WR) && ci->i_auth_cap) { + int mds_wanted; + if (ci->i_auth_cap && + (need & (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_EXCL))) { struct ceph_mds_session *s = ci->i_auth_cap->session; spin_lock(&s->s_cap_lock); session_readonly = s->s_readonly; spin_unlock(&s->s_cap_lock); } if (session_readonly) { - dout("get_cap_refs %p needed %s but mds%d readonly\n", + dout("get_cap_refs %p need %s but mds%d readonly\n", inode, ceph_cap_string(need), ci->i_auth_cap->mds); ret = -EROFS; goto out_unlock; } - if (ci->i_ceph_flags & CEPH_I_CAP_DROPPED) { - int mds_wanted; - if (READ_ONCE(mdsc->fsc->mount_state) == - CEPH_MOUNT_SHUTDOWN) { - dout("get_cap_refs %p forced umount\n", inode); - ret = -EIO; - goto out_unlock; - } - mds_wanted = __ceph_caps_mds_wanted(ci, false); - if (need & ~(mds_wanted & need)) { - dout("get_cap_refs %p caps were dropped" - " (session killed?)\n", inode); - ret = -ESTALE; - goto out_unlock; - } - if (!(file_wanted & ~mds_wanted)) - ci->i_ceph_flags &= ~CEPH_I_CAP_DROPPED; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) { + dout("get_cap_refs %p forced umount\n", inode); + ret = -EIO; + goto out_unlock; + } + mds_wanted = __ceph_caps_mds_wanted(ci, false); + if (need & ~mds_wanted) { + dout("get_cap_refs %p need %s > mds_wanted %s\n", + inode, ceph_cap_string(need), + ceph_cap_string(mds_wanted)); + ret = -ESTALE; + goto out_unlock; } - dout("get_cap_refs %p have %s needed %s\n", inode, + dout("get_cap_refs %p have %s need %s\n", inode, ceph_cap_string(have), ceph_cap_string(need)); } out_unlock: + + __ceph_touch_fmode(ci, mdsc, flags); + spin_unlock(&ci->i_ceph_lock); if (snap_rwsem_locked) up_read(&mdsc->snap_rwsem); @@ -2712,20 +2718,40 @@ static void check_max_size(struct inode *inode, loff_t endoff) ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); } +static inline int get_used_fmode(int caps) +{ + int fmode = 0; + if (caps & CEPH_CAP_FILE_RD) + fmode |= CEPH_FILE_MODE_RD; + if (caps & CEPH_CAP_FILE_WR) + fmode |= CEPH_FILE_MODE_WR; + return fmode; +} + int ceph_try_get_caps(struct inode *inode, int need, int want, bool nonblock, int *got) { - int ret; + int ret, flags; BUG_ON(need & ~CEPH_CAP_FILE_RD); - BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO|CEPH_CAP_FILE_SHARED)); - ret = ceph_pool_perm_check(inode, need); - if (ret < 0) - return ret; + BUG_ON(want & ~(CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO | + CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL | + CEPH_CAP_ANY_DIR_OPS)); + if (need) { + ret = ceph_pool_perm_check(inode, need); + if (ret < 0) + return ret; + } + + flags = get_used_fmode(need | want); + if (nonblock) + flags |= NON_BLOCKING; - ret = try_get_cap_refs(inode, need, want, 0, - (nonblock ? NON_BLOCKING : 0), got); - return ret == -EAGAIN ? 0 : ret; + ret = try_get_cap_refs(inode, need, want, 0, flags, got); + /* three special error codes */ + if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN) + ret = 0; + return ret; } /* @@ -2750,16 +2776,16 @@ int ceph_get_caps(struct file *filp, int need, int want, fi->filp_gen != READ_ONCE(fsc->filp_gen)) return -EBADF; - while (true) { - if (endoff > 0) - check_max_size(inode, endoff); + flags = get_used_fmode(need | want); - flags = atomic_read(&fi->num_locks) ? CHECK_FILELOCK : 0; + while (true) { + flags &= CEPH_FILE_MODE_MASK; + if (atomic_read(&fi->num_locks)) + flags |= CHECK_FILELOCK; _got = 0; ret = try_get_cap_refs(inode, need, want, endoff, flags, &_got); - if (ret == -EAGAIN) - continue; + WARN_ON_ONCE(ret == -EAGAIN); if (!ret) { struct ceph_mds_client *mdsc = fsc->mdsc; struct cap_wait cw; @@ -2774,6 +2800,8 @@ int ceph_get_caps(struct file *filp, int need, int want, list_add(&cw.list, &mdsc->cap_wait_list); spin_unlock(&mdsc->caps_list_lock); + /* make sure used fmode not timeout */ + ceph_get_fmode(ci, flags, FMODE_WAIT_BIAS); add_wait_queue(&ci->i_cap_wq, &wait); flags |= NON_BLOCKING; @@ -2787,6 +2815,7 @@ int ceph_get_caps(struct file *filp, int need, int want, } remove_wait_queue(&ci->i_cap_wq, &wait); + ceph_put_fmode(ci, flags, FMODE_WAIT_BIAS); spin_lock(&mdsc->caps_list_lock); list_del(&cw.list); @@ -2804,16 +2833,26 @@ int ceph_get_caps(struct file *filp, int need, int want, } if (ret < 0) { + if (ret == -EFBIG || ret == -ESTALE) { + int ret2 = ceph_wait_on_async_create(inode); + if (ret2 < 0) + return ret2; + } + if (ret == -EFBIG) { + check_max_size(inode, endoff); + continue; + } if (ret == -ESTALE) { /* session was killed, try renew caps */ - ret = ceph_renew_caps(inode); + ret = ceph_renew_caps(inode, flags); if (ret == 0) continue; } return ret; } - if (ci->i_inline_version != CEPH_INLINE_NONE && + if (S_ISREG(ci->vfs_inode.i_mode) && + ci->i_inline_version != CEPH_INLINE_NONE && (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) && i_size_read(inode) > 0) { struct page *page = @@ -2846,7 +2885,8 @@ int ceph_get_caps(struct file *filp, int need, int want, break; } - if ((_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE)) + if (S_ISREG(ci->vfs_inode.i_mode) && + (_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE)) ceph_fscache_revalidate_cookie(ci); *got = _got; @@ -2860,7 +2900,7 @@ int ceph_get_caps(struct file *filp, int need, int want, void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps) { spin_lock(&ci->i_ceph_lock); - __take_cap_refs(ci, caps, false); + ceph_take_cap_refs(ci, caps, false); spin_unlock(&ci->i_ceph_lock); } @@ -2911,6 +2951,9 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had) if (had & CEPH_CAP_FILE_CACHE) if (--ci->i_rdcache_ref == 0) last++; + if (had & CEPH_CAP_FILE_EXCL) + if (--ci->i_fx_ref == 0) + last++; if (had & CEPH_CAP_FILE_BUFFER) { if (--ci->i_wb_ref == 0) { last++; @@ -2950,7 +2993,7 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had) dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had), last ? " last" : "", put ? " put" : ""); - if (last && !flushsnaps) + if (last) ceph_check_caps(ci, 0, NULL); else if (flushsnaps) ceph_flush_snaps(ci, NULL); @@ -3032,7 +3075,7 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, spin_unlock(&ci->i_ceph_lock); if (last) { - ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); + ceph_check_caps(ci, 0, NULL); } else if (flush_snaps) { ceph_flush_snaps(ci, NULL); } @@ -3133,7 +3176,7 @@ static void handle_cap_grant(struct inode *inode, * try to invalidate (once). (If there are dirty buffers, we * will invalidate _after_ writeback.) */ - if (!S_ISDIR(inode->i_mode) && /* don't invalidate readdir cache */ + if (S_ISREG(inode->i_mode) && /* don't invalidate readdir cache */ ((cap->issued & ~newcaps) & CEPH_CAP_FILE_CACHE) && (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 && !(ci->i_wrbuffer_ref || ci->i_wb_ref)) { @@ -3297,11 +3340,12 @@ static void handle_cap_grant(struct inode *inode, ceph_cap_string(cap->issued), ceph_cap_string(newcaps), ceph_cap_string(revoking)); - if (revoking & used & CEPH_CAP_FILE_BUFFER) + if (S_ISREG(inode->i_mode) && + (revoking & used & CEPH_CAP_FILE_BUFFER)) writeback = true; /* initiate writeback; will delay ack */ - else if (revoking == CEPH_CAP_FILE_CACHE && - (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 && - queue_invalidate) + else if (queue_invalidate && + revoking == CEPH_CAP_FILE_CACHE && + (newcaps & CEPH_CAP_FILE_LAZYIO) == 0) ; /* do nothing yet, invalidation will be queued */ else if (cap == ci->i_auth_cap) check_caps = 1; /* check auth cap only */ @@ -3339,7 +3383,8 @@ static void handle_cap_grant(struct inode *inode, if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) { if (newcaps & ~extra_info->issued) wake = true; - kick_flushing_inode_caps(session->s_mdsc, session, inode); + ceph_kick_flushing_inode_caps(session, ci); + spin_unlock(&ci->i_ceph_lock); up_read(&session->s_mdsc->snap_rwsem); } else { spin_unlock(&ci->i_ceph_lock); @@ -3367,10 +3412,10 @@ static void handle_cap_grant(struct inode *inode, wake_up_all(&ci->i_cap_wq); if (check_caps == 1) - ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_AUTHONLY, + ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL, session); else if (check_caps == 2) - ceph_check_caps(ci, CHECK_CAPS_NODELAY, session); + ceph_check_caps(ci, CHECK_CAPS_NOINVAL, session); else mutex_unlock(&session->s_mutex); } @@ -3619,8 +3664,6 @@ retry: goto out_unlock; if (target < 0) { - if (cap->mds_wanted | cap->issued) - ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; __ceph_remove_cap(cap, false); goto out_unlock; } @@ -3668,7 +3711,7 @@ retry: /* add placeholder for the export tagert */ int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0; tcap = new_cap; - ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0, + ceph_add_cap(inode, tsession, t_cap_id, issued, 0, t_seq - 1, t_mseq, (u64)-1, flag, &new_cap); if (!list_empty(&ci->i_cap_flush_list) && @@ -3773,7 +3816,7 @@ retry: __ceph_caps_issued(ci, &issued); issued |= __ceph_caps_dirty(ci); - ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq, + ceph_add_cap(inode, session, cap_id, caps, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH, &new_cap); ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL; @@ -4047,7 +4090,6 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) { struct inode *inode; struct ceph_inode_info *ci; - int flags = CHECK_CAPS_NODELAY; dout("check_delayed_caps\n"); while (1) { @@ -4067,7 +4109,7 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) if (inode) { dout("check_delayed_caps on %p\n", inode); - ceph_check_caps(ci, flags, NULL); + ceph_check_caps(ci, 0, NULL); /* avoid calling iput_final() in tick thread */ ceph_async_iput(inode); } @@ -4092,7 +4134,7 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc) ihold(inode); dout("flush_dirty_caps %p\n", inode); spin_unlock(&mdsc->cap_dirty_lock); - ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH, NULL); + ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL); iput(inode); spin_lock(&mdsc->cap_dirty_lock); } @@ -4100,14 +4142,31 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc) dout("flush_dirty_caps done\n"); } -void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode) +void __ceph_touch_fmode(struct ceph_inode_info *ci, + struct ceph_mds_client *mdsc, int fmode) +{ + unsigned long now = jiffies; + if (fmode & CEPH_FILE_MODE_RD) + ci->i_last_rd = now; + if (fmode & CEPH_FILE_MODE_WR) + ci->i_last_wr = now; + /* queue periodic check */ + if (fmode && + __ceph_is_any_real_caps(ci) && + list_empty(&ci->i_cap_delay_list)) + __cap_delay_requeue(mdsc, ci); +} + +void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) { int i; int bits = (fmode << 1) | 1; + spin_lock(&ci->i_ceph_lock); for (i = 0; i < CEPH_FILE_MODE_BITS; i++) { if (bits & (1 << i)) - ci->i_nr_by_mode[i]++; + ci->i_nr_by_mode[i] += count; } + spin_unlock(&ci->i_ceph_lock); } /* @@ -4115,26 +4174,18 @@ void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode) * we may need to release capabilities to the MDS (or schedule * their delayed release). */ -void ceph_put_fmode(struct ceph_inode_info *ci, int fmode) +void ceph_put_fmode(struct ceph_inode_info *ci, int fmode, int count) { - int i, last = 0; + int i; int bits = (fmode << 1) | 1; spin_lock(&ci->i_ceph_lock); for (i = 0; i < CEPH_FILE_MODE_BITS; i++) { if (bits & (1 << i)) { - BUG_ON(ci->i_nr_by_mode[i] == 0); - if (--ci->i_nr_by_mode[i] == 0) - last++; + BUG_ON(ci->i_nr_by_mode[i] < count); + ci->i_nr_by_mode[i] -= count; } } - dout("put_fmode %p fmode %d {%d,%d,%d,%d}\n", - &ci->vfs_inode, fmode, - ci->i_nr_by_mode[0], ci->i_nr_by_mode[1], - ci->i_nr_by_mode[2], ci->i_nr_by_mode[3]); spin_unlock(&ci->i_ceph_lock); - - if (last && ci->i_vino.snap == CEPH_NOSNAP) - ceph_check_caps(ci, 0, NULL); } /* @@ -4152,7 +4203,6 @@ int ceph_drop_caps_for_unlink(struct inode *inode) if (inode->i_nlink == 1) { drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN); - ci->i_ceph_flags |= CEPH_I_NODELAY; if (__ceph_caps_dirty(ci)) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; @@ -4208,8 +4258,6 @@ int ceph_encode_inode_release(void **p, struct inode *inode, if (force || (cap->issued & drop)) { if (cap->issued & drop) { int wanted = __ceph_caps_wanted(ci); - if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0) - wanted |= cap->mds_wanted; dout("encode_inode_release %p cap %p " "%s -> %s, wanted %s -> %s\n", inode, cap, ceph_cap_string(cap->issued), diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fb7cabd98e7b..481ac97b4d25 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -218,10 +218,10 @@ static int mds_sessions_show(struct seq_file *s, void *ptr) return 0; } -CEPH_DEFINE_SHOW_FUNC(mdsmap_show) -CEPH_DEFINE_SHOW_FUNC(mdsc_show) -CEPH_DEFINE_SHOW_FUNC(caps_show) -CEPH_DEFINE_SHOW_FUNC(mds_sessions_show) +DEFINE_SHOW_ATTRIBUTE(mdsmap); +DEFINE_SHOW_ATTRIBUTE(mdsc); +DEFINE_SHOW_ATTRIBUTE(caps); +DEFINE_SHOW_ATTRIBUTE(mds_sessions); /* @@ -281,25 +281,25 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) 0400, fsc->client->debugfs_dir, fsc, - &mdsmap_show_fops); + &mdsmap_fops); fsc->debugfs_mds_sessions = debugfs_create_file("mds_sessions", 0400, fsc->client->debugfs_dir, fsc, - &mds_sessions_show_fops); + &mds_sessions_fops); fsc->debugfs_mdsc = debugfs_create_file("mdsc", 0400, fsc->client->debugfs_dir, fsc, - &mdsc_show_fops); + &mdsc_fops); fsc->debugfs_caps = debugfs_create_file("caps", 0400, fsc->client->debugfs_dir, fsc, - &caps_show_fops); + &caps_fops); } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index d0cd0aba5843..d594c2627430 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -335,8 +335,11 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) ctx->pos = 2; } - /* can we use the dcache? */ spin_lock(&ci->i_ceph_lock); + /* request Fx cap. if have Fx, we don't need to release Fs cap + * for later create/unlink. */ + __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_WR); + /* can we use the dcache? */ if (ceph_test_mount_opt(fsc, DCACHE) && !ceph_test_mount_opt(fsc, NOASYNCREADDIR) && ceph_snap(inode) != CEPH_SNAPDIR && @@ -752,7 +755,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, struct ceph_dentry_info *di = ceph_dentry(dentry); spin_lock(&ci->i_ceph_lock); - dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags); + dout(" dir %p flags are 0x%lx\n", dir, ci->i_ceph_flags); if (strncmp(dentry->d_name.name, fsc->mount_options->snapdir_name, dentry->d_name.len) && @@ -760,6 +763,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, ceph_test_mount_opt(fsc, DCACHE) && __ceph_dir_is_complete(ci) && (__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) { + __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD); spin_unlock(&ci->i_ceph_lock); dout(" dir %p complete, -ENOENT\n", dir); d_add(dentry, NULL); @@ -1036,6 +1040,78 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, return err; } +static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req) +{ + int result = req->r_err ? req->r_err : + le32_to_cpu(req->r_reply_info.head->result); + + if (result == -EJUKEBOX) + goto out; + + /* If op failed, mark everyone involved for errors */ + if (result) { + int pathlen; + u64 base; + char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, + &base, 0); + + /* mark error on parent + clear complete */ + mapping_set_error(req->r_parent->i_mapping, result); + ceph_dir_clear_complete(req->r_parent); + + /* drop the dentry -- we don't know its status */ + if (!d_unhashed(req->r_dentry)) + d_drop(req->r_dentry); + + /* mark inode itself for an error (since metadata is bogus) */ + mapping_set_error(req->r_old_inode->i_mapping, result); + + pr_warn("ceph: async unlink failure path=(%llx)%s result=%d!\n", + base, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path(path, pathlen); + } +out: + iput(req->r_old_inode); + ceph_mdsc_release_dir_caps(req); +} + +static int get_caps_for_async_unlink(struct inode *dir, struct dentry *dentry) +{ + struct ceph_inode_info *ci = ceph_inode(dir); + struct ceph_dentry_info *di; + int got = 0, want = CEPH_CAP_FILE_EXCL | CEPH_CAP_DIR_UNLINK; + + spin_lock(&ci->i_ceph_lock); + if ((__ceph_caps_issued(ci, NULL) & want) == want) { + ceph_take_cap_refs(ci, want, false); + got = want; + } + spin_unlock(&ci->i_ceph_lock); + + /* If we didn't get anything, return 0 */ + if (!got) + return 0; + + spin_lock(&dentry->d_lock); + di = ceph_dentry(dentry); + /* + * - We are holding Fx, which implies Fs caps. + * - Only support async unlink for primary linkage + */ + if (atomic_read(&ci->i_shared_gen) != di->lease_shared_gen || + !(di->flags & CEPH_DENTRY_PRIMARY_LINK)) + want = 0; + spin_unlock(&dentry->d_lock); + + /* Do we still want what we've got? */ + if (want == got) + return got; + + ceph_put_cap_refs(ci, got); + return 0; +} + /* * rmdir and unlink are differ only by the metadata op code */ @@ -1045,6 +1121,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) struct ceph_mds_client *mdsc = fsc->mdsc; struct inode *inode = d_inode(dentry); struct ceph_mds_request *req; + bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS); int err = -EROFS; int op; @@ -1059,6 +1136,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) CEPH_MDS_OP_RMDIR : CEPH_MDS_OP_UNLINK; } else goto out; +retry: req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1067,13 +1145,39 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) req->r_dentry = dget(dentry); req->r_num_caps = 2; req->r_parent = dir; - set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_dentry_drop = CEPH_CAP_FILE_SHARED; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; req->r_inode_drop = ceph_drop_caps_for_unlink(inode); - err = ceph_mdsc_do_request(mdsc, dir, req); - if (!err && !req->r_reply_info.head->is_dentry) - d_delete(dentry); + + if (try_async && op == CEPH_MDS_OP_UNLINK && + (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) { + dout("async unlink on %lu/%.*s caps=%s", dir->i_ino, + dentry->d_name.len, dentry->d_name.name, + ceph_cap_string(req->r_dir_caps)); + set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags); + req->r_callback = ceph_async_unlink_cb; + req->r_old_inode = d_inode(dentry); + ihold(req->r_old_inode); + err = ceph_mdsc_submit_request(mdsc, dir, req); + if (!err) { + /* + * We have enough caps, so we assume that the unlink + * will succeed. Fix up the target inode and dcache. + */ + drop_nlink(inode); + d_delete(dentry); + } else if (err == -EJUKEBOX) { + try_async = false; + ceph_mdsc_put_request(req); + goto retry; + } + } else { + set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); + err = ceph_mdsc_do_request(mdsc, dir, req); + if (!err && !req->r_reply_info.head->is_dentry) + d_delete(dentry); + } + ceph_mdsc_put_request(req); out: return err; @@ -1411,6 +1515,7 @@ void ceph_invalidate_dentry_lease(struct dentry *dentry) spin_lock(&dentry->d_lock); di->time = jiffies; di->lease_shared_gen = 0; + di->flags &= ~CEPH_DENTRY_PRIMARY_LINK; __dentry_lease_unlist(di); spin_unlock(&dentry->d_lock); } @@ -1520,7 +1625,8 @@ static int __dir_lease_try_check(const struct dentry *dentry) /* * Check if directory-wide content lease/cap is valid. */ -static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry) +static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry, + struct ceph_mds_client *mdsc) { struct ceph_inode_info *ci = ceph_inode(dir); int valid; @@ -1528,7 +1634,10 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry) spin_lock(&ci->i_ceph_lock); valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1); - shared_gen = atomic_read(&ci->i_shared_gen); + if (valid) { + __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD); + shared_gen = atomic_read(&ci->i_shared_gen); + } spin_unlock(&ci->i_ceph_lock); if (valid) { struct ceph_dentry_info *di; @@ -1554,6 +1663,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) int valid = 0; struct dentry *parent; struct inode *dir, *inode; + struct ceph_mds_client *mdsc; if (flags & LOOKUP_RCU) { parent = READ_ONCE(dentry->d_parent); @@ -1570,6 +1680,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry, dentry, inode, ceph_dentry(dentry)->offset); + mdsc = ceph_sb_to_client(dir->i_sb)->mdsc; + /* always trust cached snapped dentries, snapdir dentry */ if (ceph_snap(dir) != CEPH_NOSNAP) { dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry, @@ -1581,7 +1693,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) valid = dentry_lease_is_valid(dentry, flags); if (valid == -ECHILD) return valid; - if (valid || dir_lease_is_valid(dir, dentry)) { + if (valid || dir_lease_is_valid(dir, dentry, mdsc)) { if (inode) valid = ceph_is_any_caps(inode); else @@ -1590,8 +1702,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) } if (!valid) { - struct ceph_mds_client *mdsc = - ceph_sb_to_client(dir->i_sb)->mdsc; struct ceph_mds_request *req; int op, err; u32 mask; diff --git a/fs/ceph/export.c b/fs/ceph/export.c index b6bfa94332c3..79dc06881e78 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -315,6 +315,11 @@ static struct dentry *__get_parent(struct super_block *sb, req->r_num_caps = 1; err = ceph_mdsc_do_request(mdsc, NULL, req); + if (err) { + ceph_mdsc_put_request(req); + return ERR_PTR(err); + } + inode = req->r_target_inode; if (inode) ihold(inode); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 5a478cd06e11..4a5ccbb7e808 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -212,10 +212,8 @@ static int ceph_init_file_info(struct inode *inode, struct file *file, if (isdir) { struct ceph_dir_file_info *dfi = kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL); - if (!dfi) { - ceph_put_fmode(ci, fmode); /* clean up */ + if (!dfi) return -ENOMEM; - } file->private_data = dfi; fi = &dfi->file_info; @@ -223,15 +221,15 @@ static int ceph_init_file_info(struct inode *inode, struct file *file, dfi->readdir_cache_idx = -1; } else { fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL); - if (!fi) { - ceph_put_fmode(ci, fmode); /* clean up */ + if (!fi) return -ENOMEM; - } file->private_data = fi; } + ceph_get_fmode(ci, fmode, 1); fi->fmode = fmode; + spin_lock_init(&fi->rw_contexts_lock); INIT_LIST_HEAD(&fi->rw_contexts); fi->meta_err = errseq_sample(&ci->i_meta_err); @@ -263,7 +261,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) case S_IFLNK: dout("init_file %p %p 0%o (symlink)\n", inode, file, inode->i_mode); - ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */ break; default: @@ -273,7 +270,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) * we need to drop the open ref now, since we don't * have .release set to ceph_release. */ - ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */ BUG_ON(inode->i_fop->release == ceph_release); /* call the proper open fop */ @@ -285,14 +281,15 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) /* * try renew caps after session gets killed. */ -int ceph_renew_caps(struct inode *inode) +int ceph_renew_caps(struct inode *inode, int fmode) { - struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req; int err, flags, wanted; spin_lock(&ci->i_ceph_lock); + __ceph_touch_fmode(ci, mdsc, fmode); wanted = __ceph_caps_file_wanted(ci); if (__ceph_is_any_real_caps(ci) && (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) { @@ -326,7 +323,6 @@ int ceph_renew_caps(struct inode *inode) req->r_inode = inode; ihold(inode); req->r_num_caps = 1; - req->r_fmode = -1; err = ceph_mdsc_do_request(mdsc, NULL, req); ceph_mdsc_put_request(req); @@ -372,9 +368,6 @@ int ceph_open(struct inode *inode, struct file *file) /* trivially open snapdir */ if (ceph_snap(inode) == CEPH_SNAPDIR) { - spin_lock(&ci->i_ceph_lock); - __ceph_get_fmode(ci, fmode); - spin_unlock(&ci->i_ceph_lock); return ceph_init_file(inode, file, fmode); } @@ -392,7 +385,7 @@ int ceph_open(struct inode *inode, struct file *file) dout("open %p fmode %d want %s issued %s using existing\n", inode, fmode, ceph_cap_string(wanted), ceph_cap_string(issued)); - __ceph_get_fmode(ci, fmode); + __ceph_touch_fmode(ci, mdsc, fmode); spin_unlock(&ci->i_ceph_lock); /* adjust wanted? */ @@ -404,7 +397,7 @@ int ceph_open(struct inode *inode, struct file *file) return ceph_init_file(inode, file, fmode); } else if (ceph_snap(inode) != CEPH_NOSNAP && (ci->i_snap_caps & wanted) == wanted) { - __ceph_get_fmode(ci, fmode); + __ceph_touch_fmode(ci, mdsc, fmode); spin_unlock(&ci->i_ceph_lock); return ceph_init_file(inode, file, fmode); } @@ -430,6 +423,236 @@ out: return err; } +/* Clone the layout from a synchronous create, if the dir now has Dc caps */ +static void +cache_file_layout(struct inode *dst, struct inode *src) +{ + struct ceph_inode_info *cdst = ceph_inode(dst); + struct ceph_inode_info *csrc = ceph_inode(src); + + spin_lock(&cdst->i_ceph_lock); + if ((__ceph_caps_issued(cdst, NULL) & CEPH_CAP_DIR_CREATE) && + !ceph_file_layout_is_valid(&cdst->i_cached_layout)) { + memcpy(&cdst->i_cached_layout, &csrc->i_layout, + sizeof(cdst->i_cached_layout)); + rcu_assign_pointer(cdst->i_cached_layout.pool_ns, + ceph_try_get_string(csrc->i_layout.pool_ns)); + } + spin_unlock(&cdst->i_ceph_lock); +} + +/* + * Try to set up an async create. We need caps, a file layout, and inode number, + * and either a lease on the dentry or complete dir info. If any of those + * criteria are not satisfied, then return false and the caller can go + * synchronous. + */ +static int try_prep_async_create(struct inode *dir, struct dentry *dentry, + struct ceph_file_layout *lo, u64 *pino) +{ + struct ceph_inode_info *ci = ceph_inode(dir); + struct ceph_dentry_info *di = ceph_dentry(dentry); + int got = 0, want = CEPH_CAP_FILE_EXCL | CEPH_CAP_DIR_CREATE; + u64 ino; + + spin_lock(&ci->i_ceph_lock); + /* No auth cap means no chance for Dc caps */ + if (!ci->i_auth_cap) + goto no_async; + + /* Any delegated inos? */ + if (xa_empty(&ci->i_auth_cap->session->s_delegated_inos)) + goto no_async; + + if (!ceph_file_layout_is_valid(&ci->i_cached_layout)) + goto no_async; + + if ((__ceph_caps_issued(ci, NULL) & want) != want) + goto no_async; + + if (d_in_lookup(dentry)) { + if (!__ceph_dir_is_complete(ci)) + goto no_async; + spin_lock(&dentry->d_lock); + di->lease_shared_gen = atomic_read(&ci->i_shared_gen); + spin_unlock(&dentry->d_lock); + } else if (atomic_read(&ci->i_shared_gen) != + READ_ONCE(di->lease_shared_gen)) { + goto no_async; + } + + ino = ceph_get_deleg_ino(ci->i_auth_cap->session); + if (!ino) + goto no_async; + + *pino = ino; + ceph_take_cap_refs(ci, want, false); + memcpy(lo, &ci->i_cached_layout, sizeof(*lo)); + rcu_assign_pointer(lo->pool_ns, + ceph_try_get_string(ci->i_cached_layout.pool_ns)); + got = want; +no_async: + spin_unlock(&ci->i_ceph_lock); + return got; +} + +static void restore_deleg_ino(struct inode *dir, u64 ino) +{ + struct ceph_inode_info *ci = ceph_inode(dir); + struct ceph_mds_session *s = NULL; + + spin_lock(&ci->i_ceph_lock); + if (ci->i_auth_cap) + s = ceph_get_mds_session(ci->i_auth_cap->session); + spin_unlock(&ci->i_ceph_lock); + if (s) { + int err = ceph_restore_deleg_ino(s, ino); + if (err) + pr_warn("ceph: unable to restore delegated ino 0x%llx to session: %d\n", + ino, err); + ceph_put_mds_session(s); + } +} + +static void ceph_async_create_cb(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req) +{ + int result = req->r_err ? req->r_err : + le32_to_cpu(req->r_reply_info.head->result); + + if (result == -EJUKEBOX) + goto out; + + mapping_set_error(req->r_parent->i_mapping, result); + + if (result) { + struct dentry *dentry = req->r_dentry; + int pathlen; + u64 base; + char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, + &base, 0); + + ceph_dir_clear_complete(req->r_parent); + if (!d_unhashed(dentry)) + d_drop(dentry); + + /* FIXME: start returning I/O errors on all accesses? */ + pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n", + base, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path(path, pathlen); + } + + if (req->r_target_inode) { + struct ceph_inode_info *ci = ceph_inode(req->r_target_inode); + u64 ino = ceph_vino(req->r_target_inode).ino; + + if (req->r_deleg_ino != ino) + pr_warn("%s: inode number mismatch! err=%d deleg_ino=0x%llx target=0x%llx\n", + __func__, req->r_err, req->r_deleg_ino, ino); + mapping_set_error(req->r_target_inode->i_mapping, result); + + spin_lock(&ci->i_ceph_lock); + if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { + ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE; + wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT); + } + ceph_kick_flushing_inode_caps(req->r_session, ci); + spin_unlock(&ci->i_ceph_lock); + } else { + pr_warn("%s: no req->r_target_inode for 0x%llx\n", __func__, + req->r_deleg_ino); + } +out: + ceph_mdsc_release_dir_caps(req); +} + +static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, + struct file *file, umode_t mode, + struct ceph_mds_request *req, + struct ceph_acl_sec_ctx *as_ctx, + struct ceph_file_layout *lo) +{ + int ret; + char xattr_buf[4]; + struct ceph_mds_reply_inode in = { }; + struct ceph_mds_reply_info_in iinfo = { .in = &in }; + struct ceph_inode_info *ci = ceph_inode(dir); + struct inode *inode; + struct timespec64 now; + struct ceph_vino vino = { .ino = req->r_deleg_ino, + .snap = CEPH_NOSNAP }; + + ktime_get_real_ts64(&now); + + inode = ceph_get_inode(dentry->d_sb, vino); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + iinfo.inline_version = CEPH_INLINE_NONE; + iinfo.change_attr = 1; + ceph_encode_timespec64(&iinfo.btime, &now); + + iinfo.xattr_len = ARRAY_SIZE(xattr_buf); + iinfo.xattr_data = xattr_buf; + memset(iinfo.xattr_data, 0, iinfo.xattr_len); + + in.ino = cpu_to_le64(vino.ino); + in.snapid = cpu_to_le64(CEPH_NOSNAP); + in.version = cpu_to_le64(1); // ??? + in.cap.caps = in.cap.wanted = cpu_to_le32(CEPH_CAP_ALL_FILE); + in.cap.cap_id = cpu_to_le64(1); + in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino); + in.cap.flags = CEPH_CAP_FLAG_AUTH; + in.ctime = in.mtime = in.atime = iinfo.btime; + in.mode = cpu_to_le32((u32)mode); + in.truncate_seq = cpu_to_le32(1); + in.truncate_size = cpu_to_le64(-1ULL); + in.xattr_version = cpu_to_le64(1); + in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid())); + in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ? + dir->i_gid : current_fsgid())); + in.nlink = cpu_to_le32(1); + in.max_size = cpu_to_le64(lo->stripe_unit); + + ceph_file_layout_to_legacy(lo, &in.layout); + + ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session, + req->r_fmode, NULL); + if (ret) { + dout("%s failed to fill inode: %d\n", __func__, ret); + ceph_dir_clear_complete(dir); + if (!d_unhashed(dentry)) + d_drop(dentry); + if (inode->i_state & I_NEW) + discard_new_inode(inode); + } else { + struct dentry *dn; + + dout("%s d_adding new inode 0x%llx to 0x%lx/%s\n", __func__, + vino.ino, dir->i_ino, dentry->d_name.name); + ceph_dir_clear_ordered(dir); + ceph_init_inode_acls(inode, as_ctx); + if (inode->i_state & I_NEW) { + /* + * If it's not I_NEW, then someone created this before + * we got here. Assume the server is aware of it at + * that point and don't worry about setting + * CEPH_I_ASYNC_CREATE. + */ + ceph_inode(inode)->i_ceph_flags = CEPH_I_ASYNC_CREATE; + unlock_new_inode(inode); + } + if (d_in_lookup(dentry) || d_really_is_negative(dentry)) { + if (!d_unhashed(dentry)) + d_drop(dentry); + dn = d_splice_alias(inode, dentry); + WARN_ON_ONCE(dn && dn != dentry); + } + file->f_mode |= FMODE_CREATED; + ret = finish_open(file, dentry, ceph_open); + } + return ret; +} /* * Do a lookup + open with a single request. If we get a non-existent @@ -443,6 +666,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, struct ceph_mds_request *req; struct dentry *dn; struct ceph_acl_sec_ctx as_ctx = {}; + bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS); int mask; int err; @@ -466,7 +690,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, /* If it's not being looked up, it's negative */ return -ENOENT; } - +retry: /* do the open */ req = prepare_open_request(dir->i_sb, flags, mode); if (IS_ERR(req)) { @@ -475,21 +699,43 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, } req->r_dentry = dget(dentry); req->r_num_caps = 2; + mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; + if (ceph_security_xattr_wanted(dir)) + mask |= CEPH_CAP_XATTR_SHARED; + req->r_args.open.mask = cpu_to_le32(mask); + req->r_parent = dir; + if (flags & O_CREAT) { + struct ceph_file_layout lo; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (as_ctx.pagelist) { req->r_pagelist = as_ctx.pagelist; as_ctx.pagelist = NULL; } + if (try_async && + (req->r_dir_caps = + try_prep_async_create(dir, dentry, &lo, + &req->r_deleg_ino))) { + set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags); + req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL); + req->r_callback = ceph_async_create_cb; + err = ceph_mdsc_submit_request(mdsc, dir, req); + if (!err) { + err = ceph_finish_async_create(dir, dentry, + file, mode, req, + &as_ctx, &lo); + } else if (err == -EJUKEBOX) { + restore_deleg_ino(dir, req->r_deleg_ino); + ceph_mdsc_put_request(req); + try_async = false; + goto retry; + } + goto out_req; + } } - mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; - if (ceph_security_xattr_wanted(dir)) - mask |= CEPH_CAP_XATTR_SHARED; - req->r_args.open.mask = cpu_to_le32(mask); - - req->r_parent = dir; set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); err = ceph_mdsc_do_request(mdsc, (flags & (O_CREAT|O_TRUNC)) ? dir : NULL, @@ -518,14 +764,15 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, } else { dout("atomic_open finish_open on dn %p\n", dn); if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) { - ceph_init_inode_acls(d_inode(dentry), &as_ctx); + struct inode *newino = d_inode(dentry); + + cache_file_layout(dir, newino); + ceph_init_inode_acls(newino, &as_ctx); file->f_mode |= FMODE_CREATED; } err = finish_open(file, dentry, ceph_open); } out_req: - if (!req->r_err && req->r_target_inode) - ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode); ceph_mdsc_put_request(req); out_ctx: ceph_release_acl_sec_ctx(&as_ctx); @@ -542,7 +789,7 @@ int ceph_release(struct inode *inode, struct file *file) dout("release inode %p dir file %p\n", inode, file); WARN_ON(!list_empty(&dfi->file_info.rw_contexts)); - ceph_put_fmode(ci, dfi->file_info.fmode); + ceph_put_fmode(ci, dfi->file_info.fmode, 1); if (dfi->last_readdir) ceph_mdsc_put_request(dfi->last_readdir); @@ -554,7 +801,8 @@ int ceph_release(struct inode *inode, struct file *file) dout("release inode %p regular file %p\n", inode, file); WARN_ON(!list_empty(&fi->rw_contexts)); - ceph_put_fmode(ci, fi->fmode); + ceph_put_fmode(ci, fi->fmode, 1); + kmem_cache_free(ceph_file_cachep, fi); } @@ -1567,7 +1815,7 @@ retry_snap: if (dirty) __mark_inode_dirty(inode, dirty); if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos)) - ceph_check_caps(ci, CHECK_CAPS_NODELAY, NULL); + ceph_check_caps(ci, 0, NULL); } dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n", @@ -1944,6 +2192,71 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode, return 0; } +static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off, + struct ceph_inode_info *dst_ci, u64 *dst_off, + struct ceph_fs_client *fsc, + size_t len, unsigned int flags) +{ + struct ceph_object_locator src_oloc, dst_oloc; + struct ceph_object_id src_oid, dst_oid; + size_t bytes = 0; + u64 src_objnum, src_objoff, dst_objnum, dst_objoff; + u32 src_objlen, dst_objlen; + u32 object_size = src_ci->i_layout.object_size; + int ret; + + src_oloc.pool = src_ci->i_layout.pool_id; + src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns); + dst_oloc.pool = dst_ci->i_layout.pool_id; + dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns); + + while (len >= object_size) { + ceph_calc_file_object_mapping(&src_ci->i_layout, *src_off, + object_size, &src_objnum, + &src_objoff, &src_objlen); + ceph_calc_file_object_mapping(&dst_ci->i_layout, *dst_off, + object_size, &dst_objnum, + &dst_objoff, &dst_objlen); + ceph_oid_init(&src_oid); + ceph_oid_printf(&src_oid, "%llx.%08llx", + src_ci->i_vino.ino, src_objnum); + ceph_oid_init(&dst_oid); + ceph_oid_printf(&dst_oid, "%llx.%08llx", + dst_ci->i_vino.ino, dst_objnum); + /* Do an object remote copy */ + ret = ceph_osdc_copy_from(&fsc->client->osdc, + src_ci->i_vino.snap, 0, + &src_oid, &src_oloc, + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE, + &dst_oid, &dst_oloc, + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, + dst_ci->i_truncate_seq, + dst_ci->i_truncate_size, + CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + if (ret) { + if (ret == -EOPNOTSUPP) { + fsc->have_copy_from2 = false; + pr_notice("OSDs don't support copy-from2; disabling copy offload\n"); + } + dout("ceph_osdc_copy_from returned %d\n", ret); + if (!bytes) + bytes = ret; + goto out; + } + len -= object_size; + bytes += object_size; + *src_off += object_size; + *dst_off += object_size; + } + +out: + ceph_oloc_destroy(&src_oloc); + ceph_oloc_destroy(&dst_oloc); + return bytes; +} + static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, struct file *dst_file, loff_t dst_off, size_t len, unsigned int flags) @@ -1954,14 +2267,11 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, struct ceph_inode_info *dst_ci = ceph_inode(dst_inode); struct ceph_cap_flush *prealloc_cf; struct ceph_fs_client *src_fsc = ceph_inode_to_client(src_inode); - struct ceph_object_locator src_oloc, dst_oloc; - struct ceph_object_id src_oid, dst_oid; - loff_t endoff = 0, size; - ssize_t ret = -EIO; + loff_t size; + ssize_t ret = -EIO, bytes; u64 src_objnum, dst_objnum, src_objoff, dst_objoff; - u32 src_objlen, dst_objlen, object_size; + u32 src_objlen, dst_objlen; int src_got = 0, dst_got = 0, err, dirty; - bool do_final_copy = false; if (src_inode->i_sb != dst_inode->i_sb) { struct ceph_fs_client *dst_fsc = ceph_inode_to_client(dst_inode); @@ -2039,22 +2349,14 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, if (ret < 0) goto out_caps; - size = i_size_read(dst_inode); - endoff = dst_off + len; - /* Drop dst file cached pages */ ret = invalidate_inode_pages2_range(dst_inode->i_mapping, dst_off >> PAGE_SHIFT, - endoff >> PAGE_SHIFT); + (dst_off + len) >> PAGE_SHIFT); if (ret < 0) { dout("Failed to invalidate inode pages (%zd)\n", ret); ret = 0; /* XXX */ } - src_oloc.pool = src_ci->i_layout.pool_id; - src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns); - dst_oloc.pool = dst_ci->i_layout.pool_id; - dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns); - ceph_calc_file_object_mapping(&src_ci->i_layout, src_off, src_ci->i_layout.object_size, &src_objnum, &src_objoff, &src_objlen); @@ -2073,6 +2375,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, * starting at the src_off */ if (src_objoff) { + dout("Initial partial copy of %u bytes\n", src_objlen); + /* * we need to temporarily drop all caps as we'll be calling * {read,write}_iter, which will get caps again. @@ -2080,8 +2384,9 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got); ret = do_splice_direct(src_file, &src_off, dst_file, &dst_off, src_objlen, flags); - if (ret < 0) { - dout("do_splice_direct returned %d\n", err); + /* Abort on short copies or on error */ + if (ret < src_objlen) { + dout("Failed partial copy (%zd)\n", ret); goto out; } len -= ret; @@ -2094,65 +2399,27 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, if (err < 0) goto out_caps; } - object_size = src_ci->i_layout.object_size; - while (len >= object_size) { - ceph_calc_file_object_mapping(&src_ci->i_layout, src_off, - object_size, &src_objnum, - &src_objoff, &src_objlen); - ceph_calc_file_object_mapping(&dst_ci->i_layout, dst_off, - object_size, &dst_objnum, - &dst_objoff, &dst_objlen); - ceph_oid_init(&src_oid); - ceph_oid_printf(&src_oid, "%llx.%08llx", - src_ci->i_vino.ino, src_objnum); - ceph_oid_init(&dst_oid); - ceph_oid_printf(&dst_oid, "%llx.%08llx", - dst_ci->i_vino.ino, dst_objnum); - /* Do an object remote copy */ - err = ceph_osdc_copy_from( - &src_fsc->client->osdc, - src_ci->i_vino.snap, 0, - &src_oid, &src_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_NOCACHE, - &dst_oid, &dst_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, - dst_ci->i_truncate_seq, dst_ci->i_truncate_size, - CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); - if (err) { - if (err == -EOPNOTSUPP) { - src_fsc->have_copy_from2 = false; - pr_notice("OSDs don't support copy-from2; disabling copy offload\n"); - } - dout("ceph_osdc_copy_from returned %d\n", err); - if (!ret) - ret = err; - goto out_caps; - } - len -= object_size; - src_off += object_size; - dst_off += object_size; - ret += object_size; - } - if (len) - /* We still need one final local copy */ - do_final_copy = true; + size = i_size_read(dst_inode); + bytes = ceph_do_objects_copy(src_ci, &src_off, dst_ci, &dst_off, + src_fsc, len, flags); + if (bytes <= 0) { + if (!ret) + ret = bytes; + goto out_caps; + } + dout("Copied %zu bytes out of %zu\n", bytes, len); + len -= bytes; + ret += bytes; file_update_time(dst_file); inode_inc_iversion_raw(dst_inode); - if (endoff > size) { - int caps_flags = 0; - + if (dst_off > size) { /* Let the MDS know about dst file size change */ - if (ceph_quota_is_max_bytes_approaching(dst_inode, endoff)) - caps_flags |= CHECK_CAPS_NODELAY; - if (ceph_inode_set_size(dst_inode, endoff)) - caps_flags |= CHECK_CAPS_AUTHONLY; - if (caps_flags) - ceph_check_caps(dst_ci, caps_flags, NULL); + if (ceph_inode_set_size(dst_inode, dst_off) || + ceph_quota_is_max_bytes_approaching(dst_inode, dst_off)) + ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY, NULL); } /* Mark Fw dirty */ spin_lock(&dst_ci->i_ceph_lock); @@ -2165,15 +2432,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, out_caps: put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got); - if (do_final_copy) { - err = do_splice_direct(src_file, &src_off, dst_file, - &dst_off, len, flags); - if (err < 0) { - dout("do_splice_direct returned %d\n", err); - goto out; - } - len -= err; - ret += err; + /* + * Do the final manual copy if we still have some bytes left, unless + * there were errors in remote object copies (len >= object_size). + */ + if (len && (len < src_ci->i_layout.object_size)) { + dout("Final partial copy of %zu bytes\n", len); + bytes = do_splice_direct(src_file, &src_off, dst_file, + &dst_off, len, flags); + if (bytes > 0) + ret += bytes; + else + dout("Failed partial copy (%zd)\n", bytes); } out: diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d01710a16a4a..7fef94fd1e55 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -82,10 +82,14 @@ struct inode *ceph_get_snapdir(struct inode *parent) inode->i_mode = parent->i_mode; inode->i_uid = parent->i_uid; inode->i_gid = parent->i_gid; + inode->i_mtime = parent->i_mtime; + inode->i_ctime = parent->i_ctime; + inode->i_atime = parent->i_atime; inode->i_op = &ceph_snapdir_iops; inode->i_fop = &ceph_snapdir_fops; ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */ ci->i_rbytes = 0; + ci->i_btime = ceph_inode(parent)->i_btime; if (inode->i_state & I_NEW) unlock_new_inode(inode); @@ -447,6 +451,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_max_files = 0; memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout)); + memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout)); RCU_INIT_POINTER(ci->i_layout.pool_ns, NULL); ci->i_fragtree = RB_ROOT; @@ -471,13 +476,13 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_prealloc_cap_flush = NULL; INIT_LIST_HEAD(&ci->i_cap_flush_list); init_waitqueue_head(&ci->i_cap_wq); - ci->i_hold_caps_min = 0; ci->i_hold_caps_max = 0; INIT_LIST_HEAD(&ci->i_cap_delay_list); INIT_LIST_HEAD(&ci->i_cap_snaps); ci->i_head_snapc = NULL; ci->i_snap_caps = 0; + ci->i_last_rd = ci->i_last_wr = jiffies - 3600 * HZ; for (i = 0; i < CEPH_FILE_MODE_BITS; i++) ci->i_nr_by_mode[i] = 0; @@ -496,6 +501,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_rdcache_ref = 0; ci->i_wr_ref = 0; ci->i_wb_ref = 0; + ci->i_fx_ref = 0; ci->i_wrbuffer_ref = 0; ci->i_wrbuffer_ref_head = 0; atomic_set(&ci->i_filelock_ref, 0); @@ -586,6 +592,7 @@ void ceph_evict_inode(struct inode *inode) ceph_buffer_put(ci->i_xattrs.prealloc_blob); ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns)); + ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns)); } static inline blkcnt_t calc_inode_blocks(u64 size) @@ -636,7 +643,7 @@ int ceph_fill_file_size(struct inode *inode, int issued, if ((issued & (CEPH_CAP_FILE_CACHE| CEPH_CAP_FILE_BUFFER)) || mapping_mapped(inode->i_mapping) || - __ceph_caps_file_wanted(ci)) { + __ceph_is_file_opened(ci)) { ci->i_truncate_pending++; queue_trunc = 1; } @@ -727,11 +734,11 @@ void ceph_fill_file_time(struct inode *inode, int issued, * Populate an inode based on info from mds. May be called on new or * existing inodes. */ -static int fill_inode(struct inode *inode, struct page *locked_page, - struct ceph_mds_reply_info_in *iinfo, - struct ceph_mds_reply_dirfrag *dirinfo, - struct ceph_mds_session *session, int cap_fmode, - struct ceph_cap_reservation *caps_reservation) +int ceph_fill_inode(struct inode *inode, struct page *locked_page, + struct ceph_mds_reply_info_in *iinfo, + struct ceph_mds_reply_dirfrag *dirinfo, + struct ceph_mds_session *session, int cap_fmode, + struct ceph_cap_reservation *caps_reservation) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_reply_inode *info = iinfo->in; @@ -748,7 +755,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, bool new_version = false; bool fill_inline = false; - dout("fill_inode %p ino %llx.%llx v %llu had %llu\n", + dout("%s %p ino %llx.%llx v %llu had %llu\n", __func__, inode, ceph_vinop(inode), le64_to_cpu(info->version), ci->i_version); @@ -769,7 +776,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if (iinfo->xattr_len > 4) { xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS); if (!xattr_blob) - pr_err("fill_inode ENOMEM xattr blob %d bytes\n", + pr_err("%s ENOMEM xattr blob %d bytes\n", __func__, iinfo->xattr_len); } @@ -932,8 +939,9 @@ static int fill_inode(struct inode *inode, struct page *locked_page, spin_unlock(&ci->i_ceph_lock); if (symlen != i_size_read(inode)) { - pr_err("fill_inode %llx.%llx BAD symlink " - "size %lld\n", ceph_vinop(inode), + pr_err("%s %llx.%llx BAD symlink " + "size %lld\n", __func__, + ceph_vinop(inode), i_size_read(inode)); i_size_write(inode, symlen); inode->i_blocks = calc_inode_blocks(symlen); @@ -957,7 +965,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, inode->i_fop = &ceph_dir_fops; break; default: - pr_err("fill_inode %llx.%llx BAD mode 0%o\n", + pr_err("%s %llx.%llx BAD mode 0%o\n", __func__, ceph_vinop(inode), inode->i_mode); } @@ -966,7 +974,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if (ceph_snap(inode) == CEPH_NOSNAP) { ceph_add_cap(inode, session, le64_to_cpu(info->cap.cap_id), - cap_fmode, info_caps, + info_caps, le32_to_cpu(info->cap.wanted), le32_to_cpu(info->cap.seq), le32_to_cpu(info->cap.mseq), @@ -991,13 +999,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, dout(" %p got snap_caps %s\n", inode, ceph_cap_string(info_caps)); ci->i_snap_caps |= info_caps; - if (cap_fmode >= 0) - __ceph_get_fmode(ci, cap_fmode); } - } else if (cap_fmode >= 0) { - pr_warn("mds issued no caps on %llx.%llx\n", - ceph_vinop(inode)); - __ceph_get_fmode(ci, cap_fmode); } if (iinfo->inline_version > 0 && @@ -1009,6 +1011,13 @@ static int fill_inode(struct inode *inode, struct page *locked_page, fill_inline = true; } + if (cap_fmode >= 0) { + if (!info_caps) + pr_warn("mds issued no caps on %llx.%llx\n", + ceph_vinop(inode)); + __ceph_touch_fmode(ci, mdsc, cap_fmode); + } + spin_unlock(&ci->i_ceph_lock); if (fill_inline) @@ -1050,6 +1059,7 @@ static void __update_dentry_lease(struct inode *dir, struct dentry *dentry, struct ceph_mds_session **old_lease_session) { struct ceph_dentry_info *di = ceph_dentry(dentry); + unsigned mask = le16_to_cpu(lease->mask); long unsigned duration = le32_to_cpu(lease->duration_ms); long unsigned ttl = from_time + (duration * HZ) / 1000; long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000; @@ -1061,8 +1071,13 @@ static void __update_dentry_lease(struct inode *dir, struct dentry *dentry, if (ceph_snap(dir) != CEPH_NOSNAP) return; + if (mask & CEPH_LEASE_PRIMARY_LINK) + di->flags |= CEPH_DENTRY_PRIMARY_LINK; + else + di->flags &= ~CEPH_DENTRY_PRIMARY_LINK; + di->lease_shared_gen = atomic_read(&ceph_inode(dir)->i_shared_gen); - if (duration == 0) { + if (!(mask & CEPH_LEASE_VALID)) { __ceph_dentry_dir_lease_touch(di); return; } @@ -1239,10 +1254,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) struct inode *dir = req->r_parent; if (dir) { - err = fill_inode(dir, NULL, - &rinfo->diri, rinfo->dirfrag, - session, -1, - &req->r_caps_reservation); + err = ceph_fill_inode(dir, NULL, &rinfo->diri, + rinfo->dirfrag, session, -1, + &req->r_caps_reservation); if (err < 0) goto done; } else { @@ -1307,13 +1321,14 @@ retry_lookup: goto done; } - err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL, - session, + err = ceph_fill_inode(in, req->r_locked_page, &rinfo->targeti, + NULL, session, (!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) && + !test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) && rinfo->head->result == 0) ? req->r_fmode : -1, &req->r_caps_reservation); if (err < 0) { - pr_err("fill_inode badness %p %llx.%llx\n", + pr_err("ceph_fill_inode badness %p %llx.%llx\n", in, ceph_vinop(in)); if (in->i_state & I_NEW) discard_new_inode(in); @@ -1500,10 +1515,11 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req, dout("new_inode badness got %d\n", err); continue; } - rc = fill_inode(in, NULL, &rde->inode, NULL, session, - -1, &req->r_caps_reservation); + rc = ceph_fill_inode(in, NULL, &rde->inode, NULL, session, + -1, &req->r_caps_reservation); if (rc < 0) { - pr_err("fill_inode badness on %p got %d\n", in, rc); + pr_err("ceph_fill_inode badness on %p got %d\n", + in, rc); err = rc; if (in->i_state & I_NEW) { ihold(in); @@ -1707,10 +1723,10 @@ retry_lookup: } } - ret = fill_inode(in, NULL, &rde->inode, NULL, session, - -1, &req->r_caps_reservation); + ret = ceph_fill_inode(in, NULL, &rde->inode, NULL, session, + -1, &req->r_caps_reservation); if (ret < 0) { - pr_err("fill_inode badness on %p\n", in); + pr_err("ceph_fill_inode badness on %p\n", in); if (d_really_is_negative(dn)) { /* avoid calling iput_final() in mds * dispatch threads */ @@ -1972,7 +1988,7 @@ retry: mutex_unlock(&ci->i_truncate_mutex); if (wrbuffer_refs == 0) - ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); + ceph_check_caps(ci, 0, NULL); wake_up_all(&ci->i_cap_wq); } diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index c90f03beb15d..6e061bf62ad4 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -243,11 +243,13 @@ static long ceph_ioctl_lazyio(struct file *file) struct ceph_file_info *fi = file->private_data; struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) { spin_lock(&ci->i_ceph_lock); fi->fmode |= CEPH_FILE_MODE_LAZY; ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++; + __ceph_touch_fmode(ci, mdsc, fi->fmode); spin_unlock(&ci->i_ceph_lock); dout("ioctl_layzio: file %p marked lazy\n", file); diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 544e9e85b120..d6b9166e71e4 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -210,6 +210,21 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, return 0; } +static int try_unlock_file(struct file *file, struct file_lock *fl) +{ + int err; + unsigned int orig_flags = fl->fl_flags; + fl->fl_flags |= FL_EXISTS; + err = locks_lock_file_wait(file, fl); + fl->fl_flags = orig_flags; + if (err == -ENOENT) { + if (!(orig_flags & FL_EXISTS)) + err = 0; + return err; + } + return 1; +} + /** * Attempt to set an fcntl lock. * For now, this just goes away to the server. Later it may be more awesome. @@ -255,9 +270,15 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) else lock_cmd = CEPH_LOCK_UNLOCK; + if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type) { + err = try_unlock_file(file, fl); + if (err <= 0) + return err; + } + err = ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, lock_cmd, wait, fl); if (!err) { - if (op == CEPH_MDS_OP_SETFILELOCK) { + if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->fl_type) { dout("mds locked, locking locally\n"); err = posix_lock_file(file, fl, NULL); if (err) { @@ -311,9 +332,15 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) else lock_cmd = CEPH_LOCK_UNLOCK; + if (F_UNLCK == fl->fl_type) { + err = try_unlock_file(file, fl); + if (err <= 0) + return err; + } + err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK, inode, lock_cmd, wait, fl); - if (!err) { + if (!err && F_UNLCK != fl->fl_type) { err = locks_lock_file_wait(file, fl); if (err) { ceph_lock_message(CEPH_LOCK_FLOCK, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index bbbbddf71326..486f91f9685b 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -415,21 +415,121 @@ bad: return -EIO; } + +#if BITS_PER_LONG == 64 + +#define DELEGATED_INO_AVAILABLE xa_mk_value(1) + +static int ceph_parse_deleg_inos(void **p, void *end, + struct ceph_mds_session *s) +{ + u32 sets; + + ceph_decode_32_safe(p, end, sets, bad); + dout("got %u sets of delegated inodes\n", sets); + while (sets--) { + u64 start, len, ino; + + ceph_decode_64_safe(p, end, start, bad); + ceph_decode_64_safe(p, end, len, bad); + while (len--) { + int err = xa_insert(&s->s_delegated_inos, ino = start++, + DELEGATED_INO_AVAILABLE, + GFP_KERNEL); + if (!err) { + dout("added delegated inode 0x%llx\n", + start - 1); + } else if (err == -EBUSY) { + pr_warn("ceph: MDS delegated inode 0x%llx more than once.\n", + start - 1); + } else { + return err; + } + } + } + return 0; +bad: + return -EIO; +} + +u64 ceph_get_deleg_ino(struct ceph_mds_session *s) +{ + unsigned long ino; + void *val; + + xa_for_each(&s->s_delegated_inos, ino, val) { + val = xa_erase(&s->s_delegated_inos, ino); + if (val == DELEGATED_INO_AVAILABLE) + return ino; + } + return 0; +} + +int ceph_restore_deleg_ino(struct ceph_mds_session *s, u64 ino) +{ + return xa_insert(&s->s_delegated_inos, ino, DELEGATED_INO_AVAILABLE, + GFP_KERNEL); +} +#else /* BITS_PER_LONG == 64 */ +/* + * FIXME: xarrays can't handle 64-bit indexes on a 32-bit arch. For now, just + * ignore delegated_inos on 32 bit arch. Maybe eventually add xarrays for top + * and bottom words? + */ +static int ceph_parse_deleg_inos(void **p, void *end, + struct ceph_mds_session *s) +{ + u32 sets; + + ceph_decode_32_safe(p, end, sets, bad); + if (sets) + ceph_decode_skip_n(p, end, sets * 2 * sizeof(__le64), bad); + return 0; +bad: + return -EIO; +} + +u64 ceph_get_deleg_ino(struct ceph_mds_session *s) +{ + return 0; +} + +int ceph_restore_deleg_ino(struct ceph_mds_session *s, u64 ino) +{ + return 0; +} +#endif /* BITS_PER_LONG == 64 */ + /* * parse create results */ static int parse_reply_info_create(void **p, void *end, struct ceph_mds_reply_info_parsed *info, - u64 features) + u64 features, struct ceph_mds_session *s) { + int ret; + if (features == (u64)-1 || (features & CEPH_FEATURE_REPLY_CREATE_INODE)) { - /* Malformed reply? */ if (*p == end) { + /* Malformed reply? */ info->has_create_ino = false; - } else { + } else if (test_bit(CEPHFS_FEATURE_DELEG_INO, &s->s_features)) { + u8 struct_v, struct_compat; + u32 len; + info->has_create_ino = true; + ceph_decode_8_safe(p, end, struct_v, bad); + ceph_decode_8_safe(p, end, struct_compat, bad); + ceph_decode_32_safe(p, end, len, bad); + ceph_decode_64_safe(p, end, info->ino, bad); + ret = ceph_parse_deleg_inos(p, end, s); + if (ret) + return ret; + } else { + /* legacy */ ceph_decode_64_safe(p, end, info->ino, bad); + info->has_create_ino = true; } } else { if (*p != end) @@ -448,7 +548,7 @@ bad: */ static int parse_reply_info_extra(void **p, void *end, struct ceph_mds_reply_info_parsed *info, - u64 features) + u64 features, struct ceph_mds_session *s) { u32 op = le32_to_cpu(info->head->op); @@ -457,7 +557,7 @@ static int parse_reply_info_extra(void **p, void *end, else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP) return parse_reply_info_readdir(p, end, info, features); else if (op == CEPH_MDS_OP_CREATE) - return parse_reply_info_create(p, end, info, features); + return parse_reply_info_create(p, end, info, features, s); else return -EIO; } @@ -465,7 +565,7 @@ static int parse_reply_info_extra(void **p, void *end, /* * parse entire mds reply */ -static int parse_reply_info(struct ceph_msg *msg, +static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg, struct ceph_mds_reply_info_parsed *info, u64 features) { @@ -490,7 +590,7 @@ static int parse_reply_info(struct ceph_msg *msg, ceph_decode_32_safe(&p, end, len, bad); if (len > 0) { ceph_decode_need(&p, end, len, bad); - err = parse_reply_info_extra(&p, p+len, info, features); + err = parse_reply_info_extra(&p, p+len, info, features, s); if (err < 0) goto out_bad; } @@ -558,6 +658,7 @@ void ceph_put_mds_session(struct ceph_mds_session *s) if (refcount_dec_and_test(&s->s_ref)) { if (s->s_auth.authorizer) ceph_auth_destroy_authorizer(s->s_auth.authorizer); + xa_destroy(&s->s_delegated_inos); kfree(s); } } @@ -645,6 +746,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, refcount_set(&s->s_ref, 1); INIT_LIST_HEAD(&s->s_waiting); INIT_LIST_HEAD(&s->s_unsafe); + xa_init(&s->s_delegated_inos); s->s_num_cap_releases = 0; s->s_cap_reconnect = 0; s->s_cap_iterator = NULL; @@ -699,6 +801,7 @@ void ceph_mdsc_release_request(struct kref *kref) struct ceph_mds_request *req = container_of(kref, struct ceph_mds_request, r_kref); + ceph_mdsc_release_dir_caps(req); destroy_reply_info(&req->r_reply_info); if (req->r_request) ceph_msg_put(req->r_request); @@ -736,7 +839,7 @@ void ceph_mdsc_release_request(struct kref *kref) put_request_session(req); ceph_unreserve_caps(req->r_mdsc, &req->r_caps_reservation); WARN_ON_ONCE(!list_empty(&req->r_wait)); - kfree(req); + kmem_cache_free(ceph_mds_request_cachep, req); } DEFINE_RB_FUNCS(request, struct ceph_mds_request, r_tid, r_node) @@ -793,8 +896,13 @@ static void __register_request(struct ceph_mds_client *mdsc, mdsc->oldest_tid = req->r_tid; if (dir) { + struct ceph_inode_info *ci = ceph_inode(dir); + ihold(dir); req->r_unsafe_dir = dir; + spin_lock(&ci->i_unsafe_lock); + list_add_tail(&req->r_unsafe_dir_item, &ci->i_unsafe_dirops); + spin_unlock(&ci->i_unsafe_lock); } } @@ -822,8 +930,7 @@ static void __unregister_request(struct ceph_mds_client *mdsc, erase_request(&mdsc->request_tree, req); - if (req->r_unsafe_dir && - test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) { + if (req->r_unsafe_dir) { struct ceph_inode_info *ci = ceph_inode(req->r_unsafe_dir); spin_lock(&ci->i_unsafe_lock); list_del_init(&req->r_unsafe_dir_item); @@ -1407,8 +1514,6 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, dout("removing cap %p, ci is %p, inode is %p\n", cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); - if (cap->mds_wanted | cap->issued) - ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; __ceph_remove_cap(cap, false); if (!ci->i_auth_cap) { struct ceph_cap_flush *cf; @@ -1574,9 +1679,6 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap, /* mds did not re-issue stale cap */ spin_lock(&ci->i_ceph_lock); cap->issued = cap->implemented = CEPH_CAP_PIN; - /* make sure mds knows what we want */ - if (__ceph_caps_file_wanted(ci) & ~cap->mds_wanted) - ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; spin_unlock(&ci->i_ceph_lock); } } else if (ev == FORCE_RO) { @@ -1772,7 +1874,8 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) } /* The inode has cached pages, but it's no longer used. * we can safely drop it */ - if (wanted == 0 && used == CEPH_CAP_FILE_CACHE && + if (S_ISREG(inode->i_mode) && + wanted == 0 && used == CEPH_CAP_FILE_CACHE && !(oissued & CEPH_CAP_FILE_CACHE)) { used = 0; oissued = 0; @@ -2089,8 +2192,9 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, struct ceph_mds_request * ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode) { - struct ceph_mds_request *req = kzalloc(sizeof(*req), GFP_NOFS); + struct ceph_mds_request *req; + req = kmem_cache_zalloc(ceph_mds_request_cachep, GFP_NOFS); if (!req) return ERR_PTR(-ENOMEM); @@ -2368,7 +2472,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, head->op = cpu_to_le32(req->r_op); head->caller_uid = cpu_to_le32(from_kuid(&init_user_ns, req->r_uid)); head->caller_gid = cpu_to_le32(from_kgid(&init_user_ns, req->r_gid)); - head->ino = 0; + head->ino = cpu_to_le64(req->r_deleg_ino); head->args = req->r_args; ceph_encode_filepath(&p, end, ino1, path1); @@ -2382,7 +2486,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, if (req->r_inode_drop) releases += ceph_encode_inode_release(&p, req->r_inode ? req->r_inode : d_inode(req->r_dentry), - mds, req->r_inode_drop, req->r_inode_unless, 0); + mds, req->r_inode_drop, req->r_inode_unless, + req->r_op == CEPH_MDS_OP_READDIR); if (req->r_dentry_drop) releases += ceph_encode_dentry_release(&p, req->r_dentry, req->r_parent, mds, req->r_dentry_drop, @@ -2522,12 +2627,13 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc, rhead->oldest_client_tid = cpu_to_le64(__get_oldest_tid(mdsc)); if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) flags |= CEPH_MDS_FLAG_REPLAY; + if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags)) + flags |= CEPH_MDS_FLAG_ASYNC; if (req->r_parent) flags |= CEPH_MDS_FLAG_WANT_DENTRY; rhead->flags = cpu_to_le32(flags); rhead->num_fwd = req->r_num_fwd; rhead->num_retry = req->r_attempts - 1; - rhead->ino = 0; dout(" r_parent = %p\n", req->r_parent); return 0; @@ -2573,7 +2679,7 @@ static void __do_request(struct ceph_mds_client *mdsc, if (req->r_timeout && time_after_eq(jiffies, req->r_started + req->r_timeout)) { dout("do_request timed out\n"); - err = -EIO; + err = -ETIMEDOUT; goto finish; } if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) { @@ -2605,6 +2711,10 @@ static void __do_request(struct ceph_mds_client *mdsc, mds = __choose_mds(mdsc, req, &random); if (mds < 0 || ceph_mdsmap_get_state(mdsc->mdsmap, mds) < CEPH_MDS_STATE_ACTIVE) { + if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags)) { + err = -EJUKEBOX; + goto finish; + } dout("do_request no mds or not active, waiting for map\n"); list_add(&req->r_wait, &mdsc->waiting_for_map); return; @@ -2629,6 +2739,15 @@ static void __do_request(struct ceph_mds_client *mdsc, err = -EACCES; goto out_session; } + /* + * We cannot queue async requests since the caps and delegated + * inodes are bound to the session. Just return -EJUKEBOX and + * let the caller retry a sync request in that case. + */ + if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags)) { + err = -EJUKEBOX; + goto out_session; + } if (session->s_state == CEPH_MDS_SESSION_NEW || session->s_state == CEPH_MDS_SESSION_CLOSING) { __open_session(mdsc, session); @@ -2709,19 +2828,43 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds) int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req) { - int err; + int err = 0; /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); if (req->r_parent) { - ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + struct ceph_inode_info *ci = ceph_inode(req->r_parent); + int fmode = (req->r_op & CEPH_MDS_OP_WRITE) ? + CEPH_FILE_MODE_WR : CEPH_FILE_MODE_RD; + spin_lock(&ci->i_ceph_lock); + ceph_take_cap_refs(ci, CEPH_CAP_PIN, false); + __ceph_touch_fmode(ci, mdsc, fmode); + spin_unlock(&ci->i_ceph_lock); ihold(req->r_parent); } if (req->r_old_dentry_dir) ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); + if (req->r_inode) { + err = ceph_wait_on_async_create(req->r_inode); + if (err) { + dout("%s: wait for async create returned: %d\n", + __func__, err); + return err; + } + } + + if (!err && req->r_old_inode) { + err = ceph_wait_on_async_create(req->r_old_inode); + if (err) { + dout("%s: wait for async create returned: %d\n", + __func__, err); + return err; + } + } + dout("submit_request on %p for inode %p\n", req, dir); mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); @@ -2747,7 +2890,7 @@ static int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc, if (timeleft > 0) err = 0; else if (!timeleft) - err = -EIO; /* timed out */ + err = -ETIMEDOUT; /* timed out */ else err = timeleft; /* killed */ } @@ -2935,22 +3078,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) } else { set_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags); list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe); - if (req->r_unsafe_dir) { - struct ceph_inode_info *ci = - ceph_inode(req->r_unsafe_dir); - spin_lock(&ci->i_unsafe_lock); - list_add_tail(&req->r_unsafe_dir_item, - &ci->i_unsafe_dirops); - spin_unlock(&ci->i_unsafe_lock); - } } dout("handle_reply tid %lld result %d\n", tid, result); rinfo = &req->r_reply_info; if (test_bit(CEPHFS_FEATURE_REPLY_ENCODING, &session->s_features)) - err = parse_reply_info(msg, rinfo, (u64)-1); + err = parse_reply_info(session, msg, rinfo, (u64)-1); else - err = parse_reply_info(msg, rinfo, session->s_con.peer_features); + err = parse_reply_info(session, msg, rinfo, session->s_con.peer_features); mutex_unlock(&mdsc->mutex); mutex_lock(&session->s_mutex); @@ -3249,6 +3384,17 @@ bad: return; } +void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req) +{ + int dcaps; + + dcaps = xchg(&req->r_dir_caps, 0); + if (dcaps) { + dout("releasing r_dir_caps=%s\n", ceph_cap_string(dcaps)); + ceph_put_cap_refs(ceph_inode(req->r_parent), dcaps); + } +} + /* * called under session->mutex. */ @@ -3276,9 +3422,14 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc, continue; if (req->r_attempts == 0) continue; /* only old requests */ - if (req->r_session && - req->r_session->s_mds == session->s_mds) - __send_request(mdsc, session, req, true); + if (!req->r_session) + continue; + if (req->r_session->s_mds != session->s_mds) + continue; + + ceph_mdsc_release_dir_caps(req); + + __send_request(mdsc, session, req, true); } mutex_unlock(&mdsc->mutex); } @@ -3362,7 +3513,7 @@ fail_msg: /* * Encode information about a cap for a reconnect with the MDS. */ -static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, +static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) { union { @@ -3385,6 +3536,15 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, cap->mseq = 0; /* and migrate_seq */ cap->cap_gen = cap->session->s_cap_gen; + /* These are lost when the session goes away */ + if (S_ISDIR(inode->i_mode)) { + if (cap->issued & CEPH_CAP_DIR_CREATE) { + ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns)); + memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout)); + } + cap->issued &= ~CEPH_CAP_ANY_DIR_OPS; + } + if (recon_state->msg_version >= 2) { rec.v2.cap_id = cpu_to_le64(cap->cap_id); rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); @@ -3626,6 +3786,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, if (!reply) goto fail_nomsg; + xa_destroy(&session->s_delegated_inos); + mutex_lock(&session->s_mutex); session->s_state = CEPH_MDS_SESSION_RECONNECTING; session->s_seq = 0; @@ -3681,7 +3843,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.msg_version = 2; } /* trsaverse this session's caps */ - err = ceph_iterate_session_caps(session, encode_caps_cb, &recon_state); + err = ceph_iterate_session_caps(session, reconnect_caps_cb, &recon_state); spin_lock(&session->s_cap_lock); session->s_cap_reconnect = 0; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 27a7446e10d3..4e5be79bf080 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -23,8 +23,9 @@ enum ceph_feature_type { CEPHFS_FEATURE_RECLAIM_CLIENT, CEPHFS_FEATURE_LAZY_CAP_WANTED, CEPHFS_FEATURE_MULTI_RECONNECT, + CEPHFS_FEATURE_DELEG_INO, - CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MULTI_RECONNECT, + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO, }; /* @@ -37,6 +38,7 @@ enum ceph_feature_type { CEPHFS_FEATURE_REPLY_ENCODING, \ CEPHFS_FEATURE_LAZY_CAP_WANTED, \ CEPHFS_FEATURE_MULTI_RECONNECT, \ + CEPHFS_FEATURE_DELEG_INO, \ \ CEPHFS_FEATURE_MAX, \ } @@ -201,6 +203,7 @@ struct ceph_mds_session { struct list_head s_waiting; /* waiting requests */ struct list_head s_unsafe; /* unsafe requests */ + struct xarray s_delegated_inos; }; /* @@ -255,6 +258,7 @@ struct ceph_mds_request { #define CEPH_MDS_R_GOT_RESULT (5) /* got a result */ #define CEPH_MDS_R_DID_PREPOPULATE (6) /* prepopulated readdir */ #define CEPH_MDS_R_PARENT_LOCKED (7) /* is r_parent->i_rwsem wlocked? */ +#define CEPH_MDS_R_ASYNC (8) /* async request */ unsigned long r_req_flags; struct mutex r_fill_mutex; @@ -263,6 +267,7 @@ struct ceph_mds_request { int r_fmode; /* file mode, if expecting cap */ kuid_t r_uid; kgid_t r_gid; + int r_request_release_offset; struct timespec64 r_stamp; /* for choosing which mds to send this request to */ @@ -280,12 +285,16 @@ struct ceph_mds_request { int r_old_inode_drop, r_old_inode_unless; struct ceph_msg *r_request; /* original request */ - int r_request_release_offset; struct ceph_msg *r_reply; struct ceph_mds_reply_info_parsed r_reply_info; - struct page *r_locked_page; int r_err; + + struct page *r_locked_page; + int r_dir_caps; + int r_num_caps; + u32 r_readdir_offset; + unsigned long r_timeout; /* optional. jiffies, 0 is "wait forever" */ unsigned long r_started; /* start time to measure timeout against */ unsigned long r_request_started; /* start time for mds request only, @@ -304,6 +313,7 @@ struct ceph_mds_request { int r_num_fwd; /* number of forward attempts */ int r_resend_mds; /* mds to resend to next, if any*/ u32 r_sent_on_mseq; /* cap mseq request was sent at*/ + u64 r_deleg_ino; struct list_head r_wait; struct completion r_completion; @@ -315,10 +325,8 @@ struct ceph_mds_request { long long r_dir_release_cnt; long long r_dir_ordered_cnt; int r_readdir_cache_idx; - u32 r_readdir_offset; struct ceph_cap_reservation r_caps_reservation; - int r_num_caps; }; struct ceph_pool_perm { @@ -488,6 +496,7 @@ extern int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req); +extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req); static inline void ceph_mdsc_get_request(struct ceph_mds_request *req) { kref_get(&req->r_kref); @@ -537,4 +546,15 @@ extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc, extern int ceph_trim_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, int max_caps); + +static inline int ceph_wait_on_async_create(struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + + return wait_on_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT, + TASK_INTERRUPTIBLE); +} + +extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session); +extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino); #endif diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c7f150686a53..c9784eb1159a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -155,6 +155,7 @@ enum { Opt_acl, Opt_quotadf, Opt_copyfrom, + Opt_wsync, }; enum ceph_recover_session_mode { @@ -194,6 +195,7 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = { fsparam_string ("snapdirname", Opt_snapdirname), fsparam_string ("source", Opt_source), fsparam_u32 ("wsize", Opt_wsize), + fsparam_flag_no ("wsync", Opt_wsync), {} }; @@ -444,6 +446,12 @@ static int ceph_parse_mount_param(struct fs_context *fc, fc->sb_flags &= ~SB_POSIXACL; } break; + case Opt_wsync: + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_ASYNC_DIROPS; + else + fsopt->flags |= CEPH_MOUNT_OPT_ASYNC_DIROPS; + break; default: BUG(); } @@ -567,6 +575,9 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER) seq_show_option(m, "recover_session", "clean"); + if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) + seq_puts(m, ",nowsync"); + if (fsopt->wsize != CEPH_MAX_WRITE_SIZE) seq_printf(m, ",wsize=%u", fsopt->wsize); if (fsopt->rsize != CEPH_MAX_READ_SIZE) @@ -729,6 +740,7 @@ struct kmem_cache *ceph_cap_flush_cachep; struct kmem_cache *ceph_dentry_cachep; struct kmem_cache *ceph_file_cachep; struct kmem_cache *ceph_dir_file_cachep; +struct kmem_cache *ceph_mds_request_cachep; static void ceph_inode_init_once(void *foo) { @@ -769,6 +781,10 @@ static int __init init_caches(void) if (!ceph_dir_file_cachep) goto bad_dir_file; + ceph_mds_request_cachep = KMEM_CACHE(ceph_mds_request, SLAB_MEM_SPREAD); + if (!ceph_mds_request_cachep) + goto bad_mds_req; + error = ceph_fscache_register(); if (error) goto bad_fscache; @@ -776,6 +792,8 @@ static int __init init_caches(void) return 0; bad_fscache: + kmem_cache_destroy(ceph_mds_request_cachep); +bad_mds_req: kmem_cache_destroy(ceph_dir_file_cachep); bad_dir_file: kmem_cache_destroy(ceph_file_cachep); @@ -804,6 +822,7 @@ static void destroy_caches(void) kmem_cache_destroy(ceph_dentry_cachep); kmem_cache_destroy(ceph_file_cachep); kmem_cache_destroy(ceph_dir_file_cachep); + kmem_cache_destroy(ceph_mds_request_cachep); ceph_fscache_unregister(); } @@ -1107,6 +1126,15 @@ static void ceph_free_fc(struct fs_context *fc) static int ceph_reconfigure_fc(struct fs_context *fc) { + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + struct ceph_fs_client *fsc = ceph_sb_to_client(fc->root->d_sb); + + if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) + ceph_set_mount_opt(fsc, ASYNC_DIROPS); + else + ceph_clear_mount_opt(fsc, ASYNC_DIROPS); + sync_filesystem(fc->root->d_sb); return 0; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 037cdfb2ad4f..60aac3aee055 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -43,13 +43,16 @@ #define CEPH_MOUNT_OPT_MOUNTWAIT (1<<12) /* mount waits if no mds is up */ #define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */ #define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */ +#define CEPH_MOUNT_OPT_ASYNC_DIROPS (1<<15) /* allow async directory ops */ #define CEPH_MOUNT_OPT_DEFAULT \ (CEPH_MOUNT_OPT_DCACHE | \ CEPH_MOUNT_OPT_NOCOPYFROM) #define ceph_set_mount_opt(fsc, opt) \ - (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt; + (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt +#define ceph_clear_mount_opt(fsc, opt) \ + (fsc)->mount_options->flags &= ~CEPH_MOUNT_OPT_##opt #define ceph_test_mount_opt(fsc, opt) \ (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt)) @@ -170,9 +173,9 @@ struct ceph_cap { struct list_head caps_item; }; -#define CHECK_CAPS_NODELAY 1 /* do not delay any further */ -#define CHECK_CAPS_AUTHONLY 2 /* only check auth cap */ -#define CHECK_CAPS_FLUSH 4 /* flush any dirty caps */ +#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */ +#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */ +#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */ struct ceph_cap_flush { u64 tid; @@ -284,6 +287,7 @@ struct ceph_dentry_info { #define CEPH_DENTRY_REFERENCED 1 #define CEPH_DENTRY_LEASE_LIST 2 #define CEPH_DENTRY_SHRINK_LIST 4 +#define CEPH_DENTRY_PRIMARY_LINK 8 struct ceph_inode_xattrs_info { /* @@ -315,13 +319,14 @@ struct ceph_inode_info { u64 i_inline_version; u32 i_time_warp_seq; - unsigned i_ceph_flags; + unsigned long i_ceph_flags; atomic64_t i_release_count; atomic64_t i_ordered_count; atomic64_t i_complete_seq[2]; struct ceph_dir_layout i_dir_layout; struct ceph_file_layout i_layout; + struct ceph_file_layout i_cached_layout; // for async creates char *i_symlink; /* for dirs */ @@ -352,7 +357,6 @@ struct ceph_inode_info { struct ceph_cap_flush *i_prealloc_cap_flush; struct list_head i_cap_flush_list; wait_queue_head_t i_cap_wq; /* threads waiting on a capability */ - unsigned long i_hold_caps_min; /* jiffies */ unsigned long i_hold_caps_max; /* jiffies */ struct list_head i_cap_delay_list; /* for delayed cap release to mds */ struct ceph_cap_reservation i_cap_migration_resv; @@ -361,6 +365,8 @@ struct ceph_inode_info { dirty|flushing caps */ unsigned i_snap_caps; /* cap bits for snapped files */ + unsigned long i_last_rd; + unsigned long i_last_wr; int i_nr_by_mode[CEPH_FILE_MODE_BITS]; /* open file counts */ struct mutex i_truncate_mutex; @@ -375,7 +381,7 @@ struct ceph_inode_info { /* held references to caps */ int i_pin_ref; - int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref; + int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref, i_fx_ref; int i_wrbuffer_ref, i_wrbuffer_ref_head; atomic_t i_filelock_ref; atomic_t i_shared_gen; /* increment each time we get FILE_SHARED */ @@ -511,18 +517,18 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, * Ceph inode. */ #define CEPH_I_DIR_ORDERED (1 << 0) /* dentries in dir are ordered */ -#define CEPH_I_NODELAY (1 << 1) /* do not delay cap release */ #define CEPH_I_FLUSH (1 << 2) /* do not delay flush of dirty metadata */ #define CEPH_I_POOL_PERM (1 << 3) /* pool rd/wr bits are valid */ #define CEPH_I_POOL_RD (1 << 4) /* can read from pool */ #define CEPH_I_POOL_WR (1 << 5) /* can write to pool */ #define CEPH_I_SEC_INITED (1 << 6) /* security initialized */ -#define CEPH_I_CAP_DROPPED (1 << 7) /* caps were forcibly dropped */ -#define CEPH_I_KICK_FLUSH (1 << 8) /* kick flushing caps */ -#define CEPH_I_FLUSH_SNAPS (1 << 9) /* need flush snapss */ -#define CEPH_I_ERROR_WRITE (1 << 10) /* have seen write errors */ -#define CEPH_I_ERROR_FILELOCK (1 << 11) /* have seen file lock errors */ -#define CEPH_I_ODIRECT (1 << 12) /* inode in direct I/O mode */ +#define CEPH_I_KICK_FLUSH (1 << 7) /* kick flushing caps */ +#define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */ +#define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */ +#define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */ +#define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ +#define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ +#define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) /* * Masks of ceph inode work. @@ -674,18 +680,12 @@ extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci, extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask); extern int __ceph_caps_used(struct ceph_inode_info *ci); -extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci); - -/* - * wanted, by virtue of open file modes AND cap refs (buffered/cached data) - */ -static inline int __ceph_caps_wanted(struct ceph_inode_info *ci) +static inline bool __ceph_is_file_opened(struct ceph_inode_info *ci) { - int w = __ceph_caps_file_wanted(ci) | __ceph_caps_used(ci); - if (w & CEPH_CAP_FILE_BUFFER) - w |= CEPH_CAP_FILE_EXCL; /* we want EXCL if dirty data */ - return w; + return ci->i_nr_by_mode[0]; } +extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci); +extern int __ceph_caps_wanted(struct ceph_inode_info *ci); /* what the mds thinks we want */ extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check); @@ -899,6 +899,9 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci) } /* inode.c */ +struct ceph_mds_reply_info_in; +struct ceph_mds_reply_dirfrag; + extern const struct inode_operations ceph_file_iops; extern struct inode *ceph_alloc_inode(struct super_block *sb); @@ -914,6 +917,11 @@ extern void ceph_fill_file_time(struct inode *inode, int issued, u64 time_warp_seq, struct timespec64 *ctime, struct timespec64 *mtime, struct timespec64 *atime); +extern int ceph_fill_inode(struct inode *inode, struct page *locked_page, + struct ceph_mds_reply_info_in *iinfo, + struct ceph_mds_reply_dirfrag *dirinfo, + struct ceph_mds_session *session, int cap_fmode, + struct ceph_cap_reservation *caps_reservation); extern int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req); extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, @@ -1042,7 +1050,7 @@ extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx); extern void ceph_add_cap(struct inode *inode, struct ceph_mds_session *session, u64 cap_id, - int fmode, unsigned issued, unsigned wanted, + unsigned issued, unsigned wanted, unsigned cap, unsigned seq, u64 realmino, int flags, struct ceph_cap **new_cap); extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); @@ -1058,8 +1066,12 @@ extern void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); +void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session, + struct ceph_inode_info *ci); extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci, int mds); +extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps, + bool snap_rwsem_locked); extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps); extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had); extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, @@ -1084,8 +1096,10 @@ extern int ceph_try_get_caps(struct inode *inode, int need, int want, bool nonblock, int *got); /* for counting open files by mode */ -extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode); -extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode); +extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count); +extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count); +extern void __ceph_touch_fmode(struct ceph_inode_info *ci, + struct ceph_mds_client *mdsc, int fmode); /* addr.c */ extern const struct address_space_operations ceph_aops; @@ -1097,7 +1111,7 @@ extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); /* file.c */ extern const struct file_operations ceph_file_fops; -extern int ceph_renew_caps(struct inode *inode); +extern int ceph_renew_caps(struct inode *inode, int fmode); extern int ceph_open(struct inode *inode, struct file *file); extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned flags, umode_t mode); diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 22cf04fb32d3..604f65f4b6c5 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -202,7 +202,7 @@ config CIFS_SMB_DIRECT help Enables SMB Direct support for SMB 3.0, 3.02 and 3.1.1. SMB Direct allows transferring SMB packets over RDMA. If unsure, - say N. + say Y. config CIFS_FSCACHE bool "Provide CIFS client caching support" diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 276e4b5ea8e0..916567d770f5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -323,10 +323,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) atomic_read(&server->smbd_conn->send_credits), atomic_read(&server->smbd_conn->receive_credits), server->smbd_conn->receive_credit_target); - seq_printf(m, "\nPending send_pending: %x " - "send_payload_pending: %x", - atomic_read(&server->smbd_conn->send_pending), - atomic_read(&server->smbd_conn->send_payload_pending)); + seq_printf(m, "\nPending send_pending: %x ", + atomic_read(&server->smbd_conn->send_pending)); seq_printf(m, "\nReceive buffers count_receive_queue: %x " "count_empty_packet_queue: %x", server->smbd_conn->count_receive_queue, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 94e3ed4850b5..c31f362fa098 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1208,6 +1208,10 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, { unsigned int xid = get_xid(); ssize_t rc; + struct cifsFileInfo *cfile = dst_file->private_data; + + if (cfile->swapfile) + return -EOPNOTSUPP; rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, len, flags); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 0d956360e984..05dd3dea684b 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -426,7 +426,8 @@ struct smb_version_operations { /* generate new lease key */ void (*new_lease_key)(struct cifs_fid *); int (*generate_signingkey)(struct cifs_ses *); - int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *); + int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *, + bool allocate_crypto); int (*set_integrity)(const unsigned int, struct cifs_tcon *tcon, struct cifsFileInfo *src_file); int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, @@ -1312,6 +1313,7 @@ struct cifsFileInfo { struct tcon_link *tlink; unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ + bool swapfile:1; bool oplock_break_cancelled:1; unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 5920820bfbd0..0b1528edebcf 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4808,6 +4808,60 @@ cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter) return -EINVAL; } +static int cifs_swap_activate(struct swap_info_struct *sis, + struct file *swap_file, sector_t *span) +{ + struct cifsFileInfo *cfile = swap_file->private_data; + struct inode *inode = swap_file->f_mapping->host; + unsigned long blocks; + long long isize; + + cifs_dbg(FYI, "swap activate\n"); + + spin_lock(&inode->i_lock); + blocks = inode->i_blocks; + isize = inode->i_size; + spin_unlock(&inode->i_lock); + if (blocks*512 < isize) { + pr_warn("swap activate: swapfile has holes\n"); + return -EINVAL; + } + *span = sis->pages; + + printk_once(KERN_WARNING "Swap support over SMB3 is experimental\n"); + + /* + * TODO: consider adding ACL (or documenting how) to prevent other + * users (on this or other systems) from reading it + */ + + + /* TODO: add sk_set_memalloc(inet) or similar */ + + if (cfile) + cfile->swapfile = true; + /* + * TODO: Since file already open, we can't open with DENY_ALL here + * but we could add call to grab a byte range lock to prevent others + * from reading or writing the file + */ + + return 0; +} + +static void cifs_swap_deactivate(struct file *file) +{ + struct cifsFileInfo *cfile = file->private_data; + + cifs_dbg(FYI, "swap deactivate\n"); + + /* TODO: undo sk_set_memalloc(inet) will eventually be needed */ + + if (cfile) + cfile->swapfile = false; + + /* do we need to unpin (or unlock) the file */ +} const struct address_space_operations cifs_addr_ops = { .readpage = cifs_readpage, @@ -4821,6 +4875,13 @@ const struct address_space_operations cifs_addr_ops = { .direct_IO = cifs_direct_io, .invalidatepage = cifs_invalidate_page, .launder_page = cifs_launder_page, + /* + * TODO: investigate and if useful we could add an cifs_migratePage + * helper (under an CONFIG_MIGRATION) in the future, and also + * investigate and add an is_dirty_writeback helper if needed + */ + .swap_activate = cifs_swap_activate, + .swap_deactivate = cifs_swap_deactivate, }; /* diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 8d01ec2dca66..8fbbdcdad8ff 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2026,6 +2026,10 @@ cifs_revalidate_mapping(struct inode *inode) int rc; unsigned long *flags = &CIFS_I(inode)->flags; + /* swapfiles are not supposed to be shared */ + if (IS_SWAPFILE(inode)) + return 0; + rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable, TASK_KILLABLE); if (rc) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 19e4a5d3b4ca..50f776a8d4ba 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -246,7 +246,7 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, */ fattr->cf_mode = le32_to_cpu(info->Mode) & ~S_IFMT; - cifs_dbg(VFS, "XXX dev %d, reparse %d, mode %o", + cifs_dbg(FYI, "posix fattr: dev %d, reparse %d, mode %o", le32_to_cpu(info->DeviceId), le32_to_cpu(info->ReparseTag), le32_to_cpu(info->Mode)); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 0511aaf451d4..497afb0b9960 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -766,6 +766,20 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); spin_lock(&cifs_tcp_ses_lock); + if (tcon->tc_count <= 0) { + struct TCP_Server_Info *server = NULL; + + WARN_ONCE(tcon->tc_count < 0, "tcon refcount is negative"); + spin_unlock(&cifs_tcp_ses_lock); + + if (tcon->ses) + server = tcon->ses->server; + + cifs_server_dbg(FYI, "tid=%u: tcon is closing, skipping async close retry of fid %llu %llu\n", + tcon->tid, persistent_fid, volatile_fid); + + return 0; + } tcon->tc_count++; spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 4d1ff7b66fdc..087d5f14320b 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -55,9 +55,11 @@ extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server, extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid); extern int smb2_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server); + struct TCP_Server_Info *server, + bool allocate_crypto); extern int smb3_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server); + struct TCP_Server_Info *server, + bool allocate_crypto); extern void smb2_echo_request(struct work_struct *work); extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode); extern bool smb2_is_valid_oplock_break(char *buffer, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 20cc79e5c15d..1a6c227ada8f 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -41,14 +41,6 @@ #include "smb2glob.h" static int -smb2_crypto_shash_allocate(struct TCP_Server_Info *server) -{ - return cifs_alloc_hash("hmac(sha256)", - &server->secmech.hmacsha256, - &server->secmech.sdeschmacsha256); -} - -static int smb3_crypto_shash_allocate(struct TCP_Server_Info *server) { struct cifs_secmech *p = &server->secmech; @@ -219,7 +211,8 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) } int -smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) +smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, + bool allocate_crypto) { int rc; unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; @@ -228,6 +221,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; struct cifs_ses *ses; struct shash_desc *shash; + struct crypto_shash *hash; + struct sdesc *sdesc = NULL; struct smb_rqst drqst; ses = smb2_find_smb_ses(server, shdr->SessionId); @@ -239,24 +234,32 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE); memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE); - rc = smb2_crypto_shash_allocate(server); - if (rc) { - cifs_server_dbg(VFS, "%s: sha256 alloc failed\n", __func__); - return rc; + if (allocate_crypto) { + rc = cifs_alloc_hash("hmac(sha256)", &hash, &sdesc); + if (rc) { + cifs_server_dbg(VFS, + "%s: sha256 alloc failed\n", __func__); + return rc; + } + shash = &sdesc->shash; + } else { + hash = server->secmech.hmacsha256; + shash = &server->secmech.sdeschmacsha256->shash; } - rc = crypto_shash_setkey(server->secmech.hmacsha256, - ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE); + rc = crypto_shash_setkey(hash, ses->auth_key.response, + SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { - cifs_server_dbg(VFS, "%s: Could not update with response\n", __func__); - return rc; + cifs_server_dbg(VFS, + "%s: Could not update with response\n", + __func__); + goto out; } - shash = &server->secmech.sdeschmacsha256->shash; rc = crypto_shash_init(shash); if (rc) { cifs_server_dbg(VFS, "%s: Could not init sha256", __func__); - return rc; + goto out; } /* @@ -271,9 +274,10 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) rc = crypto_shash_update(shash, iov[0].iov_base, iov[0].iov_len); if (rc) { - cifs_server_dbg(VFS, "%s: Could not update with payload\n", - __func__); - return rc; + cifs_server_dbg(VFS, + "%s: Could not update with payload\n", + __func__); + goto out; } drqst.rq_iov++; drqst.rq_nvec--; @@ -283,6 +287,9 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (!rc) memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE); +out: + if (allocate_crypto) + cifs_free_hash(&hash, &sdesc); return rc; } @@ -504,14 +511,17 @@ generate_smb311signingkey(struct cifs_ses *ses) } int -smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) +smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, + bool allocate_crypto) { int rc; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; - struct shash_desc *shash = &server->secmech.sdesccmacaes->shash; + struct shash_desc *shash; + struct crypto_shash *hash; + struct sdesc *sdesc = NULL; struct smb_rqst drqst; u8 key[SMB3_SIGN_KEY_SIZE]; @@ -519,14 +529,24 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (rc) return 0; + if (allocate_crypto) { + rc = cifs_alloc_hash("cmac(aes)", &hash, &sdesc); + if (rc) + return rc; + + shash = &sdesc->shash; + } else { + hash = server->secmech.cmacaes; + shash = &server->secmech.sdesccmacaes->shash; + } + memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE); memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE); - rc = crypto_shash_setkey(server->secmech.cmacaes, - key, SMB2_CMACAES_SIZE); + rc = crypto_shash_setkey(hash, key, SMB2_CMACAES_SIZE); if (rc) { cifs_server_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__); - return rc; + goto out; } /* @@ -537,7 +557,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) rc = crypto_shash_init(shash); if (rc) { cifs_server_dbg(VFS, "%s: Could not init cmac aes\n", __func__); - return rc; + goto out; } /* @@ -554,7 +574,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (rc) { cifs_server_dbg(VFS, "%s: Could not update with payload\n", __func__); - return rc; + goto out; } drqst.rq_iov++; drqst.rq_nvec--; @@ -564,6 +584,9 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (!rc) memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE); +out: + if (allocate_crypto) + cifs_free_hash(&hash, &sdesc); return rc; } @@ -593,7 +616,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) return 0; } - rc = server->ops->calc_signature(rqst, server); + rc = server->ops->calc_signature(rqst, server, false); return rc; } @@ -631,9 +654,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(shdr->Signature, 0, SMB2_SIGNATURE_SIZE); - mutex_lock(&server->srv_mutex); - rc = server->ops->calc_signature(rqst, server); - mutex_unlock(&server->srv_mutex); + rc = server->ops->calc_signature(rqst, server, true); if (rc) return rc; diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 8da43a500686..1a5834a5d597 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -284,13 +284,10 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) request->sge[i].length, DMA_TO_DEVICE); - if (request->has_payload) { - if (atomic_dec_and_test(&request->info->send_payload_pending)) - wake_up(&request->info->wait_send_payload_pending); - } else { - if (atomic_dec_and_test(&request->info->send_pending)) - wake_up(&request->info->wait_send_pending); - } + if (atomic_dec_and_test(&request->info->send_pending)) + wake_up(&request->info->wait_send_pending); + + wake_up(&request->info->wait_post_send); mempool_free(request, request->info->request_mempool); } @@ -383,27 +380,6 @@ static bool process_negotiation_response( return true; } -/* - * Check and schedule to send an immediate packet - * This is used to extend credtis to remote peer to keep the transport busy - */ -static void check_and_send_immediate(struct smbd_connection *info) -{ - if (info->transport_status != SMBD_CONNECTED) - return; - - info->send_immediate = true; - - /* - * Promptly send a packet if our peer is running low on receive - * credits - */ - if (atomic_read(&info->receive_credits) < - info->receive_credit_target - 1) - queue_delayed_work( - info->workqueue, &info->send_immediate_work, 0); -} - static void smbd_post_send_credits(struct work_struct *work) { int ret = 0; @@ -453,10 +429,16 @@ static void smbd_post_send_credits(struct work_struct *work) info->new_credits_offered += ret; spin_unlock(&info->lock_new_credits_offered); - atomic_add(ret, &info->receive_credits); - - /* Check if we can post new receive and grant credits to peer */ - check_and_send_immediate(info); + /* Promptly send an immediate packet as defined in [MS-SMBD] 3.1.1.1 */ + info->send_immediate = true; + if (atomic_read(&info->receive_credits) < + info->receive_credit_target - 1) { + if (info->keep_alive_requested == KEEP_ALIVE_PENDING || + info->send_immediate) { + log_keep_alive(INFO, "send an empty message\n"); + smbd_post_send_empty(info); + } + } } /* Called from softirq, when recv is done */ @@ -551,12 +533,6 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) info->keep_alive_requested = KEEP_ALIVE_PENDING; } - /* - * Check if we need to send something to remote peer to - * grant more credits or respond to KEEP_ALIVE packet - */ - check_and_send_immediate(info); - return; default: @@ -749,7 +725,6 @@ static int smbd_post_send_negotiate_req(struct smbd_connection *info) request->sge[0].addr, request->sge[0].length, request->sge[0].lkey); - request->has_payload = false; atomic_inc(&info->send_pending); rc = ib_post_send(info->id->qp, &send_wr, NULL); if (!rc) @@ -806,45 +781,96 @@ static int manage_keep_alive_before_sending(struct smbd_connection *info) return 0; } -/* - * Build and prepare the SMBD packet header - * This function waits for avaialbe send credits and build a SMBD packet - * header. The caller then optional append payload to the packet after - * the header - * intput values - * size: the size of the payload - * remaining_data_length: remaining data to send if this is part of a - * fragmented packet - * output values - * request_out: the request allocated from this function - * return values: 0 on success, otherwise actual error code returned - */ -static int smbd_create_header(struct smbd_connection *info, - int size, int remaining_data_length, - struct smbd_request **request_out) +/* Post the send request */ +static int smbd_post_send(struct smbd_connection *info, + struct smbd_request *request) +{ + struct ib_send_wr send_wr; + int rc, i; + + for (i = 0; i < request->num_sge; i++) { + log_rdma_send(INFO, + "rdma_request sge[%d] addr=%llu length=%u\n", + i, request->sge[i].addr, request->sge[i].length); + ib_dma_sync_single_for_device( + info->id->device, + request->sge[i].addr, + request->sge[i].length, + DMA_TO_DEVICE); + } + + request->cqe.done = send_done; + + send_wr.next = NULL; + send_wr.wr_cqe = &request->cqe; + send_wr.sg_list = request->sge; + send_wr.num_sge = request->num_sge; + send_wr.opcode = IB_WR_SEND; + send_wr.send_flags = IB_SEND_SIGNALED; + + rc = ib_post_send(info->id->qp, &send_wr, NULL); + if (rc) { + log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc); + smbd_disconnect_rdma_connection(info); + rc = -EAGAIN; + } else + /* Reset timer for idle connection after packet is sent */ + mod_delayed_work(info->workqueue, &info->idle_timer_work, + info->keep_alive_interval*HZ); + + return rc; +} + +static int smbd_post_send_sgl(struct smbd_connection *info, + struct scatterlist *sgl, int data_length, int remaining_data_length) { + int num_sgs; + int i, rc; + int header_length; struct smbd_request *request; struct smbd_data_transfer *packet; - int header_length; - int rc; + int new_credits; + struct scatterlist *sg; +wait_credit: /* Wait for send credits. A SMBD packet needs one credit */ rc = wait_event_interruptible(info->wait_send_queue, atomic_read(&info->send_credits) > 0 || info->transport_status != SMBD_CONNECTED); if (rc) - return rc; + goto err_wait_credit; + + if (info->transport_status != SMBD_CONNECTED) { + log_outgoing(ERR, "disconnected not sending on wait_credit\n"); + rc = -EAGAIN; + goto err_wait_credit; + } + if (unlikely(atomic_dec_return(&info->send_credits) < 0)) { + atomic_inc(&info->send_credits); + goto wait_credit; + } + +wait_send_queue: + wait_event(info->wait_post_send, + atomic_read(&info->send_pending) < info->send_credit_target || + info->transport_status != SMBD_CONNECTED); if (info->transport_status != SMBD_CONNECTED) { - log_outgoing(ERR, "disconnected not sending\n"); - return -EAGAIN; + log_outgoing(ERR, "disconnected not sending on wait_send_queue\n"); + rc = -EAGAIN; + goto err_wait_send_queue; + } + + if (unlikely(atomic_inc_return(&info->send_pending) > + info->send_credit_target)) { + atomic_dec(&info->send_pending); + goto wait_send_queue; } - atomic_dec(&info->send_credits); request = mempool_alloc(info->request_mempool, GFP_KERNEL); if (!request) { rc = -ENOMEM; - goto err; + goto err_alloc; } request->info = info; @@ -852,8 +878,11 @@ static int smbd_create_header(struct smbd_connection *info, /* Fill in the packet header */ packet = smbd_request_payload(request); packet->credits_requested = cpu_to_le16(info->send_credit_target); - packet->credits_granted = - cpu_to_le16(manage_credits_prior_sending(info)); + + new_credits = manage_credits_prior_sending(info); + atomic_add(new_credits, &info->receive_credits); + packet->credits_granted = cpu_to_le16(new_credits); + info->send_immediate = false; packet->flags = 0; @@ -861,11 +890,11 @@ static int smbd_create_header(struct smbd_connection *info, packet->flags |= cpu_to_le16(SMB_DIRECT_RESPONSE_REQUESTED); packet->reserved = 0; - if (!size) + if (!data_length) packet->data_offset = 0; else packet->data_offset = cpu_to_le32(24); - packet->data_length = cpu_to_le32(size); + packet->data_length = cpu_to_le32(data_length); packet->remaining_data_length = cpu_to_le32(remaining_data_length); packet->padding = 0; @@ -880,7 +909,7 @@ static int smbd_create_header(struct smbd_connection *info, /* Map the packet to DMA */ header_length = sizeof(struct smbd_data_transfer); /* If this is a packet without payload, don't send padding */ - if (!size) + if (!data_length) header_length = offsetof(struct smbd_data_transfer, padding); request->num_sge = 1; @@ -889,102 +918,15 @@ static int smbd_create_header(struct smbd_connection *info, header_length, DMA_TO_DEVICE); if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) { - mempool_free(request, info->request_mempool); rc = -EIO; - goto err; + request->sge[0].addr = 0; + goto err_dma; } request->sge[0].length = header_length; request->sge[0].lkey = info->pd->local_dma_lkey; - *request_out = request; - return 0; - -err: - atomic_inc(&info->send_credits); - return rc; -} - -static void smbd_destroy_header(struct smbd_connection *info, - struct smbd_request *request) -{ - - ib_dma_unmap_single(info->id->device, - request->sge[0].addr, - request->sge[0].length, - DMA_TO_DEVICE); - mempool_free(request, info->request_mempool); - atomic_inc(&info->send_credits); -} - -/* Post the send request */ -static int smbd_post_send(struct smbd_connection *info, - struct smbd_request *request, bool has_payload) -{ - struct ib_send_wr send_wr; - int rc, i; - - for (i = 0; i < request->num_sge; i++) { - log_rdma_send(INFO, - "rdma_request sge[%d] addr=%llu length=%u\n", - i, request->sge[i].addr, request->sge[i].length); - ib_dma_sync_single_for_device( - info->id->device, - request->sge[i].addr, - request->sge[i].length, - DMA_TO_DEVICE); - } - - request->cqe.done = send_done; - - send_wr.next = NULL; - send_wr.wr_cqe = &request->cqe; - send_wr.sg_list = request->sge; - send_wr.num_sge = request->num_sge; - send_wr.opcode = IB_WR_SEND; - send_wr.send_flags = IB_SEND_SIGNALED; - - if (has_payload) { - request->has_payload = true; - atomic_inc(&info->send_payload_pending); - } else { - request->has_payload = false; - atomic_inc(&info->send_pending); - } - - rc = ib_post_send(info->id->qp, &send_wr, NULL); - if (rc) { - log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc); - if (has_payload) { - if (atomic_dec_and_test(&info->send_payload_pending)) - wake_up(&info->wait_send_payload_pending); - } else { - if (atomic_dec_and_test(&info->send_pending)) - wake_up(&info->wait_send_pending); - } - smbd_disconnect_rdma_connection(info); - rc = -EAGAIN; - } else - /* Reset timer for idle connection after packet is sent */ - mod_delayed_work(info->workqueue, &info->idle_timer_work, - info->keep_alive_interval*HZ); - - return rc; -} - -static int smbd_post_send_sgl(struct smbd_connection *info, - struct scatterlist *sgl, int data_length, int remaining_data_length) -{ - int num_sgs; - int i, rc; - struct smbd_request *request; - struct scatterlist *sg; - - rc = smbd_create_header( - info, data_length, remaining_data_length, &request); - if (rc) - return rc; - + /* Fill in the packet data payload */ num_sgs = sgl ? sg_nents(sgl) : 0; for_each_sg(sgl, sg, num_sgs, i) { request->sge[i+1].addr = @@ -994,25 +936,41 @@ static int smbd_post_send_sgl(struct smbd_connection *info, info->id->device, request->sge[i+1].addr)) { rc = -EIO; request->sge[i+1].addr = 0; - goto dma_mapping_failure; + goto err_dma; } request->sge[i+1].length = sg->length; request->sge[i+1].lkey = info->pd->local_dma_lkey; request->num_sge++; } - rc = smbd_post_send(info, request, data_length); + rc = smbd_post_send(info, request); if (!rc) return 0; -dma_mapping_failure: - for (i = 1; i < request->num_sge; i++) +err_dma: + for (i = 0; i < request->num_sge; i++) if (request->sge[i].addr) ib_dma_unmap_single(info->id->device, request->sge[i].addr, request->sge[i].length, DMA_TO_DEVICE); - smbd_destroy_header(info, request); + mempool_free(request, info->request_mempool); + + /* roll back receive credits and credits to be offered */ + spin_lock(&info->lock_new_credits_offered); + info->new_credits_offered += new_credits; + spin_unlock(&info->lock_new_credits_offered); + atomic_sub(new_credits, &info->receive_credits); + +err_alloc: + if (atomic_dec_and_test(&info->send_pending)) + wake_up(&info->wait_send_pending); + +err_wait_send_queue: + /* roll back send credits and pending */ + atomic_inc(&info->send_credits); + +err_wait_credit: return rc; } @@ -1334,25 +1292,6 @@ static void destroy_receive_buffers(struct smbd_connection *info) mempool_free(response, info->response_mempool); } -/* - * Check and send an immediate or keep alive packet - * The condition to send those packets are defined in [MS-SMBD] 3.1.1.1 - * Connection.KeepaliveRequested and Connection.SendImmediate - * The idea is to extend credits to server as soon as it becomes available - */ -static void send_immediate_work(struct work_struct *work) -{ - struct smbd_connection *info = container_of( - work, struct smbd_connection, - send_immediate_work.work); - - if (info->keep_alive_requested == KEEP_ALIVE_PENDING || - info->send_immediate) { - log_keep_alive(INFO, "send an empty message\n"); - smbd_post_send_empty(info); - } -} - /* Implement idle connection timer [MS-SMBD] 3.1.6.2 */ static void idle_connection_timer(struct work_struct *work) { @@ -1407,14 +1346,10 @@ void smbd_destroy(struct TCP_Server_Info *server) log_rdma_event(INFO, "cancelling idle timer\n"); cancel_delayed_work_sync(&info->idle_timer_work); - log_rdma_event(INFO, "cancelling send immediate work\n"); - cancel_delayed_work_sync(&info->send_immediate_work); log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); wait_event(info->wait_send_pending, atomic_read(&info->send_pending) == 0); - wait_event(info->wait_send_payload_pending, - atomic_read(&info->send_payload_pending) == 0); /* It's not posssible for upper layer to get to reassembly */ log_rdma_event(INFO, "drain the reassembly queue\n"); @@ -1744,15 +1679,13 @@ static struct smbd_connection *_smbd_get_connection( init_waitqueue_head(&info->wait_send_queue); INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer); - INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work); queue_delayed_work(info->workqueue, &info->idle_timer_work, info->keep_alive_interval*HZ); init_waitqueue_head(&info->wait_send_pending); atomic_set(&info->send_pending, 0); - init_waitqueue_head(&info->wait_send_payload_pending); - atomic_set(&info->send_payload_pending, 0); + init_waitqueue_head(&info->wait_post_send); INIT_WORK(&info->disconnect_work, smbd_disconnect_rdma_work); INIT_WORK(&info->post_send_credits_work, smbd_post_send_credits); @@ -2226,8 +2159,8 @@ done: * that means all the I/Os have been out and we are good to return */ - wait_event(info->wait_send_payload_pending, - atomic_read(&info->send_payload_pending) == 0); + wait_event(info->wait_send_pending, + atomic_read(&info->send_pending) == 0); return rc; } diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index 8ede915f2b24..a87fca82a796 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -114,8 +114,7 @@ struct smbd_connection { /* Activity accoutning */ atomic_t send_pending; wait_queue_head_t wait_send_pending; - atomic_t send_payload_pending; - wait_queue_head_t wait_send_payload_pending; + wait_queue_head_t wait_post_send; /* Receive queue */ struct list_head receive_queue; @@ -154,7 +153,6 @@ struct smbd_connection { struct workqueue_struct *workqueue; struct delayed_work idle_timer_work; - struct delayed_work send_immediate_work; /* Memory pool for preallocating buffers */ /* request pool for RDMA send */ @@ -234,9 +232,6 @@ struct smbd_request { struct smbd_connection *info; struct ib_cqe cqe; - /* true if this request carries upper layer payload */ - bool has_payload; - /* the SGE entries for this packet */ struct ib_sge sge[SMBDIRECT_MAX_SGE]; int num_sge; @@ -1038,50 +1038,43 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, return ret; } -static bool dax_range_is_aligned(struct block_device *bdev, - unsigned int offset, unsigned int length) +int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size, + struct iomap *iomap) { - unsigned short sector_size = bdev_logical_block_size(bdev); + sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); + pgoff_t pgoff; + long rc, id; + void *kaddr; + bool page_aligned = false; - if (!IS_ALIGNED(offset, sector_size)) - return false; - if (!IS_ALIGNED(length, sector_size)) - return false; - return true; -} + if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) && + IS_ALIGNED(size, PAGE_SIZE)) + page_aligned = true; -int __dax_zero_page_range(struct block_device *bdev, - struct dax_device *dax_dev, sector_t sector, - unsigned int offset, unsigned int size) -{ - if (dax_range_is_aligned(bdev, offset, size)) { - sector_t start_sector = sector + (offset >> 9); + rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff); + if (rc) + return rc; - return blkdev_issue_zeroout(bdev, start_sector, - size >> 9, GFP_NOFS, 0); - } else { - pgoff_t pgoff; - long rc, id; - void *kaddr; + id = dax_read_lock(); - rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; + if (page_aligned) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, + size >> PAGE_SHIFT); + else + rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL); + if (rc < 0) { + dax_read_unlock(id); + return rc; + } - id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); - if (rc < 0) { - dax_read_unlock(id); - return rc; - } + if (!page_aligned) { memset(kaddr + offset, 0, size); - dax_flush(dax_dev, kaddr + offset, size); - dax_read_unlock(id); + dax_flush(iomap->dax_dev, kaddr + offset, size); } + dax_read_unlock(id); return 0; } -EXPORT_SYMBOL_GPL(__dax_zero_page_range); static loff_t dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, diff --git a/fs/filesystems.c b/fs/filesystems.c index 77bf5f95362d..90b8d879fbaf 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -272,7 +272,9 @@ struct file_system_type *get_fs_type(const char *name) fs = __get_fs_type(name, len); if (!fs && (request_module("fs-%.*s", len, name) == 0)) { fs = __get_fs_type(name, len); - WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name); + if (!fs) + pr_warn_once("request_module fs-%.*s succeeded, but still no fs?\n", + len, name); } if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) { diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c index e6d554476db4..eeebe80c6be4 100644 --- a/fs/hfsplus/attributes.c +++ b/fs/hfsplus/attributes.c @@ -292,6 +292,10 @@ static int __hfsplus_delete_attr(struct inode *inode, u32 cnid, return -ENOENT; } + /* Avoid btree corruption */ + hfs_bnode_read(fd->bnode, fd->search_key, + fd->keyoffset, fd->keylength); + err = hfs_brec_remove(fd); if (err) return err; diff --git a/fs/io-wq.c b/fs/io-wq.c index cc5cf2209fb0..4023c9846860 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -17,6 +17,7 @@ #include <linux/kthread.h> #include <linux/rculist_nulls.h> #include <linux/fs_struct.h> +#include <linux/task_work.h> #include "io-wq.h" @@ -716,6 +717,9 @@ static int io_wq_manager(void *data) complete(&wq->done); while (!kthread_should_stop()) { + if (current->task_works) + task_work_run(); + for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; bool fork_worker[2] = { false, false }; @@ -738,6 +742,9 @@ static int io_wq_manager(void *data) schedule_timeout(HZ); } + if (current->task_works) + task_work_run(); + return 0; err: set_bit(IO_WQ_BIT_ERROR, &wq->state); @@ -1124,3 +1131,8 @@ void io_wq_destroy(struct io_wq *wq) if (refcount_dec_and_test(&wq->use_refs)) __io_wq_destroy(wq); } + +struct task_struct *io_wq_get_task(struct io_wq *wq) +{ + return wq->manager; +} diff --git a/fs/io-wq.h b/fs/io-wq.h index 3ee7356d6be5..5ba12de7572f 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -136,6 +136,8 @@ typedef bool (work_cancel_fn)(struct io_wq_work *, void *); enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, void *data); +struct task_struct *io_wq_get_task(struct io_wq *wq); + #if defined(CONFIG_IO_WQ) extern void io_wq_worker_sleeping(struct task_struct *); extern void io_wq_worker_running(struct task_struct *); diff --git a/fs/io_uring.c b/fs/io_uring.c index 358f97be9c7b..5190bfb6a665 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -186,14 +186,23 @@ struct fixed_file_table { struct file **files; }; +struct fixed_file_ref_node { + struct percpu_ref refs; + struct list_head node; + struct list_head file_list; + struct fixed_file_data *file_data; + struct work_struct work; +}; + struct fixed_file_data { struct fixed_file_table *table; struct io_ring_ctx *ctx; + struct percpu_ref *cur_refs; struct percpu_ref refs; - struct llist_head put_llist; - struct work_struct ref_work; struct completion done; + struct list_head ref_list; + spinlock_t lock; }; struct io_buffer { @@ -317,6 +326,8 @@ struct io_ring_ctx { spinlock_t inflight_lock; struct list_head inflight_list; } ____cacheline_aligned_in_smp; + + struct work_struct exit_work; }; /* @@ -599,6 +610,7 @@ struct io_kiocb { }; struct io_async_ctx *io; + int cflags; bool needs_fixed_file; u8 opcode; @@ -606,10 +618,8 @@ struct io_kiocb { struct list_head list; unsigned int flags; refcount_t refs; - union { - struct task_struct *task; - unsigned long fsize; - }; + struct task_struct *task; + unsigned long fsize; u64 user_data; u32 result; u32 sequence; @@ -618,6 +628,8 @@ struct io_kiocb { struct list_head inflight_entry; + struct percpu_ref *fixed_file_refs; + union { /* * Only commands that never go async can use the below fields, @@ -629,7 +641,6 @@ struct io_kiocb { struct callback_head task_work; struct hlist_node hash_node; struct async_poll *apoll; - int cflags; }; struct io_wq_work work; }; @@ -848,7 +859,6 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_files_update *ip, unsigned nr_args); static int io_grab_files(struct io_kiocb *req); -static void io_ring_file_ref_flush(struct fixed_file_data *data); static void io_cleanup_req(struct io_kiocb *req); static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, int fd, struct file **out_file, bool fixed); @@ -1285,8 +1295,8 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx) return NULL; } -static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, - struct io_submit_state *state) +static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx, + struct io_submit_state *state) { gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct io_kiocb *req; @@ -1319,41 +1329,20 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, req = state->reqs[state->free_reqs]; } -got_it: - req->io = NULL; - req->file = NULL; - req->ctx = ctx; - req->flags = 0; - /* one is dropped after submission, the other at completion */ - refcount_set(&req->refs, 2); - req->result = 0; - INIT_IO_WORK(&req->work, io_wq_submit_work); return req; fallback: - req = io_get_fallback_req(ctx); - if (req) - goto got_it; - percpu_ref_put(&ctx->refs); - return NULL; + return io_get_fallback_req(ctx); } static inline void io_put_file(struct io_kiocb *req, struct file *file, bool fixed) { if (fixed) - percpu_ref_put(&req->ctx->file_data->refs); + percpu_ref_put(req->fixed_file_refs); else fput(file); } -static void __io_req_do_free(struct io_kiocb *req) -{ - if (likely(!io_is_fallback_req(req))) - kmem_cache_free(req_cachep, req); - else - clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req); -} - static void __io_req_aux_free(struct io_kiocb *req) { if (req->flags & REQ_F_NEED_CLEANUP) @@ -1362,6 +1351,8 @@ static void __io_req_aux_free(struct io_kiocb *req) kfree(req->io); if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); + if (req->task) + put_task_struct(req->task); io_req_work_drop_env(req); } @@ -1382,7 +1373,10 @@ static void __io_free_req(struct io_kiocb *req) } percpu_ref_put(&req->ctx->refs); - __io_req_do_free(req); + if (likely(!io_is_fallback_req(req))) + kmem_cache_free(req_cachep, req); + else + clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req); } struct req_batch { @@ -1393,21 +1387,18 @@ struct req_batch { static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb) { - int fixed_refs = rb->to_free; - if (!rb->to_free) return; if (rb->need_iter) { int i, inflight = 0; unsigned long flags; - fixed_refs = 0; for (i = 0; i < rb->to_free; i++) { struct io_kiocb *req = rb->reqs[i]; if (req->flags & REQ_F_FIXED_FILE) { req->file = NULL; - fixed_refs++; + percpu_ref_put(req->fixed_file_refs); } if (req->flags & REQ_F_INFLIGHT) inflight++; @@ -1433,8 +1424,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb) } do_free: kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs); - if (fixed_refs) - percpu_ref_put_many(&ctx->file_data->refs, fixed_refs); percpu_ref_put_many(&ctx->refs, rb->to_free); rb->to_free = rb->need_iter = 0; } @@ -1738,11 +1727,24 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_free_req_many(ctx, &rb); } +static void io_iopoll_queue(struct list_head *again) +{ + struct io_kiocb *req; + + do { + req = list_first_entry(again, struct io_kiocb, list); + list_del(&req->list); + refcount_inc(&req->refs); + io_queue_async_work(req); + } while (!list_empty(again)); +} + static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, long min) { struct io_kiocb *req, *tmp; LIST_HEAD(done); + LIST_HEAD(again); bool spin; int ret; @@ -1757,9 +1759,9 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, struct kiocb *kiocb = &req->rw.kiocb; /* - * Move completed entries to our local list. If we find a - * request that requires polling, break out and complete - * the done list first, if we have entries there. + * Move completed and retryable entries to our local lists. + * If we find a request that requires polling, break out + * and complete those lists first, if we have entries there. */ if (req->flags & REQ_F_IOPOLL_COMPLETED) { list_move_tail(&req->list, &done); @@ -1768,6 +1770,13 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, if (!list_empty(&done)) break; + if (req->result == -EAGAIN) { + list_move_tail(&req->list, &again); + continue; + } + if (!list_empty(&again)) + break; + ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); if (ret < 0) break; @@ -1780,6 +1789,9 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, if (!list_empty(&done)) io_iopoll_complete(ctx, nr_events, &done); + if (!list_empty(&again)) + io_iopoll_queue(&again); + return ret; } @@ -2465,8 +2477,9 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, req->io->rw.iov = iovec; if (!req->io->rw.iov) { req->io->rw.iov = req->io->rw.fast_iov; - memcpy(req->io->rw.iov, fast_iov, - sizeof(struct iovec) * iter->nr_segs); + if (req->io->rw.iov != fast_iov) + memcpy(req->io->rw.iov, fast_iov, + sizeof(struct iovec) * iter->nr_segs); } else { req->flags |= REQ_F_NEED_CLEANUP; } @@ -2920,7 +2933,7 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (sqe->flags & IOSQE_FIXED_FILE) + if (req->flags & REQ_F_FIXED_FILE) return -EBADF; if (req->flags & REQ_F_NEED_CLEANUP) return 0; @@ -2929,6 +2942,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->open.how.mode = READ_ONCE(sqe->len); fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); req->open.how.flags = READ_ONCE(sqe->open_flags); + if (force_o_largefile()) + req->open.how.flags |= O_LARGEFILE; req->open.filename = getname(fname); if (IS_ERR(req->open.filename)) { @@ -2951,7 +2966,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (sqe->flags & IOSQE_FIXED_FILE) + if (req->flags & REQ_F_FIXED_FILE) return -EBADF; if (req->flags & REQ_F_NEED_CLEANUP) return 0; @@ -3305,7 +3320,7 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (sqe->flags & IOSQE_FIXED_FILE) + if (req->flags & REQ_F_FIXED_FILE) return -EBADF; if (req->flags & REQ_F_NEED_CLEANUP) return 0; @@ -3382,7 +3397,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) return -EINVAL; - if (sqe->flags & IOSQE_FIXED_FILE) + if (req->flags & REQ_F_FIXED_FILE) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); @@ -3481,14 +3496,11 @@ static void __io_sync_file_range(struct io_kiocb *req) static void io_sync_file_range_finish(struct io_wq_work **workptr) { struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); - struct io_kiocb *nxt = NULL; if (io_req_cancelled(req)) return; __io_sync_file_range(req); io_put_req(req); /* put submission ref */ - if (nxt) - io_wq_assign_next(workptr, nxt); } static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) @@ -4114,6 +4126,7 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, __poll_t mask, task_work_func_t func) { struct task_struct *tsk; + int ret; /* for instances that support it check for an event match first: */ if (mask && !(mask & poll->events)) @@ -4127,11 +4140,15 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, req->result = mask; init_task_work(&req->task_work, func); /* - * If this fails, then the task is exiting. If that is the case, then - * the exit check will ultimately cancel these work items. Hence we - * don't need to check here and handle it specifically. + * If this fails, then the task is exiting. Punt to one of the io-wq + * threads to ensure the work gets run, we can't always rely on exit + * cancelation taking care of this. */ - task_work_add(tsk, &req->task_work, true); + ret = task_work_add(tsk, &req->task_work, true); + if (unlikely(ret)) { + tsk = io_wq_get_task(req->ctx->io_wq); + task_work_add(tsk, &req->task_work, true); + } wake_up_process(tsk); return 1; } @@ -4251,10 +4268,7 @@ static bool io_arm_poll_handler(struct io_kiocb *req) req->flags |= REQ_F_POLLED; memcpy(&apoll->work, &req->work, sizeof(req->work)); - /* - * Don't need a reference here, as we're adding it to the task - * task_works list. If the task exits, the list is pruned. - */ + get_task_struct(current); req->task = current; req->apoll = apoll; INIT_HLIST_NODE(&req->hash_node); @@ -4407,8 +4421,20 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error) static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt) { struct io_ring_ctx *ctx = req->ctx; + struct io_poll_iocb *poll = &req->poll; + + if (!req->result && !READ_ONCE(poll->canceled)) { + struct poll_table_struct pt = { ._key = poll->events }; + + req->result = vfs_poll(req->file, &pt) & poll->events; + } spin_lock_irq(&ctx->completion_lock); + if (!req->result && !READ_ONCE(poll->canceled)) { + add_wait_queue(poll->head, &poll->wait); + spin_unlock_irq(&ctx->completion_lock); + return; + } hash_del(&req->hash_node); io_poll_complete(req, req->result, 0); req->flags |= REQ_F_COMP_LOCKED; @@ -4465,10 +4491,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; - /* - * Don't need a reference here, as we're adding it to the task - * task_works list. If the task exits, the list is pruned. - */ + get_task_struct(current); req->task = current; return 0; } @@ -5331,7 +5354,8 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, file = io_file_from_index(ctx, fd); if (!file) return -EBADF; - percpu_ref_get(&ctx->file_data->refs); + req->fixed_file_refs = ctx->file_data->cur_refs; + percpu_ref_get(req->fixed_file_refs); } else { trace_io_uring_file_get(ctx, fd); file = __io_file_get(state, fd); @@ -5344,15 +5368,10 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, } static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - const struct io_uring_sqe *sqe) + int fd, unsigned int flags) { - unsigned flags; - int fd; bool fixed; - flags = READ_ONCE(sqe->flags); - fd = READ_ONCE(sqe->fd); - if (!io_req_needs_file(req, fd)) return 0; @@ -5594,7 +5613,7 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, { struct io_ring_ctx *ctx = req->ctx; unsigned int sqe_flags; - int ret, id; + int ret, id, fd; sqe_flags = READ_ONCE(sqe->flags); @@ -5625,7 +5644,8 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, IOSQE_ASYNC | IOSQE_FIXED_FILE | IOSQE_BUFFER_SELECT); - ret = io_req_set_file(state, req, sqe); + fd = READ_ONCE(sqe->fd); + ret = io_req_set_file(state, req, fd, sqe_flags); if (unlikely(ret)) { err_req: io_cqring_add_event(req, ret); @@ -5741,8 +5761,7 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) * used, it's important that those reads are done through READ_ONCE() to * prevent a re-load down the line. */ -static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe **sqe_ptr) +static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) { u32 *sq_array = ctx->sq_array; unsigned head; @@ -5756,25 +5775,40 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req, * though the application is the one updating it. */ head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]); - if (likely(head < ctx->sq_entries)) { - /* - * All io need record the previous position, if LINK vs DARIN, - * it can be used to mark the position of the first IO in the - * link list. - */ - req->sequence = ctx->cached_sq_head; - *sqe_ptr = &ctx->sq_sqes[head]; - req->opcode = READ_ONCE((*sqe_ptr)->opcode); - req->user_data = READ_ONCE((*sqe_ptr)->user_data); - ctx->cached_sq_head++; - return true; - } + if (likely(head < ctx->sq_entries)) + return &ctx->sq_sqes[head]; /* drop invalid entries */ - ctx->cached_sq_head++; ctx->cached_sq_dropped++; WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped); - return false; + return NULL; +} + +static inline void io_consume_sqe(struct io_ring_ctx *ctx) +{ + ctx->cached_sq_head++; +} + +static void io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + /* + * All io need record the previous position, if LINK vs DARIN, + * it can be used to mark the position of the first IO in the + * link list. + */ + req->sequence = ctx->cached_sq_head; + req->opcode = READ_ONCE(sqe->opcode); + req->user_data = READ_ONCE(sqe->user_data); + req->io = NULL; + req->file = NULL; + req->ctx = ctx; + req->flags = 0; + /* one is dropped after submission, the other at completion */ + refcount_set(&req->refs, 2); + req->task = NULL; + req->result = 0; + INIT_IO_WORK(&req->work, io_wq_submit_work); } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, @@ -5812,17 +5846,20 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, struct io_kiocb *req; int err; - req = io_get_req(ctx, statep); + sqe = io_get_sqe(ctx); + if (unlikely(!sqe)) { + io_consume_sqe(ctx); + break; + } + req = io_alloc_req(ctx, statep); if (unlikely(!req)) { if (!submitted) submitted = -EAGAIN; break; } - if (!io_get_sqring(ctx, req, &sqe)) { - __io_req_do_free(req); - break; - } + io_init_req(ctx, req, sqe); + io_consume_sqe(ctx); /* will complete beyond this point, count as submitted */ submitted++; @@ -5962,6 +5999,7 @@ static int io_sq_thread(void *data) } if (current->task_works) { task_work_run(); + finish_wait(&ctx->sqo_wait, &wait); continue; } if (signal_pending(current)) @@ -6124,43 +6162,36 @@ static void io_file_ref_kill(struct percpu_ref *ref) complete(&data->done); } -static void io_file_ref_exit_and_free(struct work_struct *work) -{ - struct fixed_file_data *data; - - data = container_of(work, struct fixed_file_data, ref_work); - - /* - * Ensure any percpu-ref atomic switch callback has run, it could have - * been in progress when the files were being unregistered. Once - * that's done, we can safely exit and free the ref and containing - * data structure. - */ - rcu_barrier(); - percpu_ref_exit(&data->refs); - kfree(data); -} - static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { struct fixed_file_data *data = ctx->file_data; + struct fixed_file_ref_node *ref_node = NULL; unsigned nr_tables, i; + unsigned long flags; if (!data) return -ENXIO; - percpu_ref_kill_and_confirm(&data->refs, io_file_ref_kill); - flush_work(&data->ref_work); + spin_lock_irqsave(&data->lock, flags); + if (!list_empty(&data->ref_list)) + ref_node = list_first_entry(&data->ref_list, + struct fixed_file_ref_node, node); + spin_unlock_irqrestore(&data->lock, flags); + if (ref_node) + percpu_ref_kill(&ref_node->refs); + + percpu_ref_kill(&data->refs); + + /* wait for all refs nodes to complete */ wait_for_completion(&data->done); - io_ring_file_ref_flush(data); __io_sqe_files_unregister(ctx); nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); for (i = 0; i < nr_tables; i++) kfree(data->table[i].files); kfree(data->table); - INIT_WORK(&data->ref_work, io_file_ref_exit_and_free); - queue_work(system_wq, &data->ref_work); + percpu_ref_exit(&data->refs); + kfree(data); ctx->file_data = NULL; ctx->nr_user_files = 0; return 0; @@ -6204,13 +6235,6 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) struct sk_buff *skb; int i, nr_files; - if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { - unsigned long inflight = ctx->user->unix_inflight + nr; - - if (inflight > task_rlimit(current, RLIMIT_NOFILE)) - return -EMFILE; - } - fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); if (!fpl) return -ENOMEM; @@ -6385,46 +6409,72 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) } struct io_file_put { - struct llist_node llist; + struct list_head list; struct file *file; }; -static void io_ring_file_ref_flush(struct fixed_file_data *data) +static void io_file_put_work(struct work_struct *work) { + struct fixed_file_ref_node *ref_node; + struct fixed_file_data *file_data; + struct io_ring_ctx *ctx; struct io_file_put *pfile, *tmp; - struct llist_node *node; + unsigned long flags; - while ((node = llist_del_all(&data->put_llist)) != NULL) { - llist_for_each_entry_safe(pfile, tmp, node, llist) { - io_ring_file_put(data->ctx, pfile->file); - kfree(pfile); - } + ref_node = container_of(work, struct fixed_file_ref_node, work); + file_data = ref_node->file_data; + ctx = file_data->ctx; + + list_for_each_entry_safe(pfile, tmp, &ref_node->file_list, list) { + list_del_init(&pfile->list); + io_ring_file_put(ctx, pfile->file); + kfree(pfile); } + + spin_lock_irqsave(&file_data->lock, flags); + list_del_init(&ref_node->node); + spin_unlock_irqrestore(&file_data->lock, flags); + + percpu_ref_exit(&ref_node->refs); + kfree(ref_node); + percpu_ref_put(&file_data->refs); } -static void io_ring_file_ref_switch(struct work_struct *work) +static void io_file_data_ref_zero(struct percpu_ref *ref) { - struct fixed_file_data *data; + struct fixed_file_ref_node *ref_node; + + ref_node = container_of(ref, struct fixed_file_ref_node, refs); - data = container_of(work, struct fixed_file_data, ref_work); - io_ring_file_ref_flush(data); - percpu_ref_switch_to_percpu(&data->refs); + queue_work(system_wq, &ref_node->work); } -static void io_file_data_ref_zero(struct percpu_ref *ref) +static struct fixed_file_ref_node *alloc_fixed_file_ref_node( + struct io_ring_ctx *ctx) { - struct fixed_file_data *data; + struct fixed_file_ref_node *ref_node; - data = container_of(ref, struct fixed_file_data, refs); + ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); + if (!ref_node) + return ERR_PTR(-ENOMEM); + + if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero, + 0, GFP_KERNEL)) { + kfree(ref_node); + return ERR_PTR(-ENOMEM); + } + INIT_LIST_HEAD(&ref_node->node); + INIT_LIST_HEAD(&ref_node->file_list); + INIT_WORK(&ref_node->work, io_file_put_work); + ref_node->file_data = ctx->file_data; + return ref_node; - /* - * We can't safely switch from inside this context, punt to wq. If - * the table ref is going away, the table is being unregistered. - * Don't queue up the async work for that case, the caller will - * handle it. - */ - if (!percpu_ref_is_dying(&data->refs)) - queue_work(system_wq, &data->ref_work); +} + +static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node) +{ + percpu_ref_exit(&ref_node->refs); + kfree(ref_node); } static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, @@ -6435,6 +6485,8 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, struct file *file; int fd, ret = 0; unsigned i; + struct fixed_file_ref_node *ref_node; + unsigned long flags; if (ctx->file_data) return -EBUSY; @@ -6448,6 +6500,8 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -ENOMEM; ctx->file_data->ctx = ctx; init_completion(&ctx->file_data->done); + INIT_LIST_HEAD(&ctx->file_data->ref_list); + spin_lock_init(&ctx->file_data->lock); nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); ctx->file_data->table = kcalloc(nr_tables, @@ -6459,15 +6513,13 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -ENOMEM; } - if (percpu_ref_init(&ctx->file_data->refs, io_file_data_ref_zero, + if (percpu_ref_init(&ctx->file_data->refs, io_file_ref_kill, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { kfree(ctx->file_data->table); kfree(ctx->file_data); ctx->file_data = NULL; return -ENOMEM; } - ctx->file_data->put_llist.first = NULL; - INIT_WORK(&ctx->file_data->ref_work, io_ring_file_ref_switch); if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) { percpu_ref_exit(&ctx->file_data->refs); @@ -6530,9 +6582,22 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, } ret = io_sqe_files_scm(ctx); - if (ret) + if (ret) { io_sqe_files_unregister(ctx); + return ret; + } + + ref_node = alloc_fixed_file_ref_node(ctx); + if (IS_ERR(ref_node)) { + io_sqe_files_unregister(ctx); + return PTR_ERR(ref_node); + } + ctx->file_data->cur_refs = &ref_node->refs; + spin_lock_irqsave(&ctx->file_data->lock, flags); + list_add(&ref_node->node, &ctx->file_data->ref_list); + spin_unlock_irqrestore(&ctx->file_data->lock, flags); + percpu_ref_get(&ctx->file_data->refs); return ret; } @@ -6579,30 +6644,21 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } -static void io_atomic_switch(struct percpu_ref *ref) -{ - struct fixed_file_data *data; - - /* - * Juggle reference to ensure we hit zero, if needed, so we can - * switch back to percpu mode - */ - data = container_of(ref, struct fixed_file_data, refs); - percpu_ref_put(&data->refs); - percpu_ref_get(&data->refs); -} - static int io_queue_file_removal(struct fixed_file_data *data, - struct file *file) + struct file *file) { struct io_file_put *pfile; + struct percpu_ref *refs = data->cur_refs; + struct fixed_file_ref_node *ref_node; pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); if (!pfile) return -ENOMEM; + ref_node = container_of(refs, struct fixed_file_ref_node, refs); pfile->file = file; - llist_add(&pfile->llist, &data->put_llist); + list_add(&pfile->list, &ref_node->file_list); + return 0; } @@ -6611,17 +6667,23 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, unsigned nr_args) { struct fixed_file_data *data = ctx->file_data; - bool ref_switch = false; + struct fixed_file_ref_node *ref_node; struct file *file; __s32 __user *fds; int fd, i, err; __u32 done; + unsigned long flags; + bool needs_switch = false; if (check_add_overflow(up->offset, nr_args, &done)) return -EOVERFLOW; if (done > ctx->nr_user_files) return -EINVAL; + ref_node = alloc_fixed_file_ref_node(ctx); + if (IS_ERR(ref_node)) + return PTR_ERR(ref_node); + done = 0; fds = u64_to_user_ptr(up->fds); while (nr_args) { @@ -6642,7 +6704,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (err) break; table->files[index] = NULL; - ref_switch = true; + needs_switch = true; } if (fd != -1) { file = fget(fd); @@ -6673,11 +6735,19 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, up->offset++; } - if (ref_switch) - percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch); + if (needs_switch) { + percpu_ref_kill(data->cur_refs); + spin_lock_irqsave(&data->lock, flags); + list_add(&ref_node->node, &data->ref_list); + data->cur_refs = &ref_node->refs; + spin_unlock_irqrestore(&data->lock, flags); + percpu_ref_get(&ctx->file_data->refs); + } else + destroy_fixed_file_ref_node(ref_node); return done ? done : err; } + static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { @@ -7203,6 +7273,18 @@ static int io_remove_personalities(int id, void *p, void *data) return 0; } +static void io_ring_exit_work(struct work_struct *work) +{ + struct io_ring_ctx *ctx; + + ctx = container_of(work, struct io_ring_ctx, exit_work); + if (ctx->rings) + io_cqring_overflow_flush(ctx, true); + + wait_for_completion(&ctx->completions[0]); + io_ring_ctx_free(ctx); +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); @@ -7230,8 +7312,8 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) if (ctx->rings) io_cqring_overflow_flush(ctx, true); idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); - wait_for_completion(&ctx->completions[0]); - io_ring_ctx_free(ctx); + INIT_WORK(&ctx->exit_work, io_ring_exit_work); + queue_work(system_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f080f542911b..89e21961d1ad 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -302,6 +302,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (!ctx->bio || !is_contig || bio_full(ctx->bio, plen)) { gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); + gfp_t orig_gfp = gfp; int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; if (ctx->bio) @@ -310,6 +311,13 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (ctx->is_readahead) /* same as readahead_gfp_mask */ gfp |= __GFP_NORETRY | __GFP_NOWARN; ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs)); + /* + * If the bio_alloc fails, try it again for a single page to + * avoid having to deal with partial page reads. This emulates + * what do_mpage_readpage does. + */ + if (!ctx->bio) + ctx->bio = bio_alloc(orig_gfp, 1); ctx->bio->bi_opf = REQ_OP_READ; if (ctx->is_readahead) ctx->bio->bi_opf |= REQ_RAHEAD; @@ -975,13 +983,6 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap); } -static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes, - struct iomap *iomap) -{ - return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, - iomap_sector(iomap, pos & PAGE_MASK), offset, bytes); -} - static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, void *data, struct iomap *iomap, struct iomap *srcmap) @@ -1001,7 +1002,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, bytes = min_t(loff_t, PAGE_SIZE - offset, count); if (IS_DAX(inode)) - status = iomap_dax_zero(pos, offset, bytes, iomap); + status = dax_iomap_zero(pos, offset, bytes, iomap); else status = iomap_zero(inode, pos, offset, bytes, iomap, srcmap); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 25f135572fc8..e7ddbce48321 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -501,6 +501,7 @@ pnfs_alloc_ds_commits_list(struct list_head *list, rcu_read_lock(); pnfs_put_commit_array(array, cinfo->inode); } + rcu_read_unlock(); return ret; } diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 65b3abbcce4e..2f834add165b 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7402,6 +7402,10 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_inline_data *idata = &di->id2.i_data; + /* No need to punch hole beyond i_size. */ + if (start >= i_size_read(inode)) + return 0; + if (end > i_size_read(inode)) end = i_size_read(inode); diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index c740159d9ad1..af375e049aae 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -346,23 +346,8 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { int ret; - struct orangefs_read_options *ro; - orangefs_stats.reads++; - /* - * Remember how they set "count" in read(2) or pread(2) or whatever - - * users can use count as a knob to control orangefs io size and later - * we can try to help them fill as many pages as possible in readpage. - */ - if (!iocb->ki_filp->private_data) { - iocb->ki_filp->private_data = kmalloc(sizeof *ro, GFP_KERNEL); - if (!iocb->ki_filp->private_data) - return(ENOMEM); - ro = iocb->ki_filp->private_data; - ro->blksiz = iter->count; - } - down_read(&file_inode(iocb->ki_filp)->i_rwsem); ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp)); if (ret) @@ -650,12 +635,6 @@ static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl) return rc; } -static int orangefs_file_open(struct inode * inode, struct file *file) -{ - file->private_data = NULL; - return generic_file_open(inode, file); -} - static int orangefs_flush(struct file *file, fl_owner_t id) { /* @@ -666,19 +645,8 @@ static int orangefs_flush(struct file *file, fl_owner_t id) * on an explicit fsync call. This duplicates historical OrangeFS * behavior. */ - struct inode *inode = file->f_mapping->host; int r; - kfree(file->private_data); - file->private_data = NULL; - - if (inode->i_state & I_DIRTY_TIME) { - spin_lock(&inode->i_lock); - inode->i_state &= ~I_DIRTY_TIME; - spin_unlock(&inode->i_lock); - mark_inode_dirty_sync(inode); - } - r = filemap_write_and_wait_range(file->f_mapping, 0, LLONG_MAX); if (r > 0) return 0; @@ -694,7 +662,7 @@ const struct file_operations orangefs_file_operations = { .lock = orangefs_lock, .unlocked_ioctl = orangefs_ioctl, .mmap = orangefs_file_mmap, - .open = orangefs_file_open, + .open = generic_file_open, .flush = orangefs_flush, .release = orangefs_file_release, .fsync = orangefs_fsync, diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 961c0fd8675a..12ae630fbed7 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -259,46 +259,19 @@ static int orangefs_readpage(struct file *file, struct page *page) pgoff_t index; /* which page */ struct page *next_page; char *kaddr; - struct orangefs_read_options *ro = file->private_data; loff_t read_size; - loff_t roundedup; int buffer_index = -1; /* orangefs shared memory slot */ int slot_index; /* index into slot */ int remaining; /* - * If they set some miniscule size for "count" in read(2) - * (for example) then let's try to read a page, or the whole file - * if it is smaller than a page. Once "count" goes over a page - * then lets round up to the highest page size multiple that is - * less than or equal to "count" and do that much orangefs IO and - * try to fill as many pages as we can from it. - * - * "count" should be represented in ro->blksiz. - * - * inode->i_size = file size. + * Get up to this many bytes from Orangefs at a time and try + * to fill them into the page cache at once. Tests with dd made + * this seem like a reasonable static number, if there was + * interest perhaps this number could be made setable through + * sysfs... */ - if (ro) { - if (ro->blksiz < PAGE_SIZE) { - if (inode->i_size < PAGE_SIZE) - read_size = inode->i_size; - else - read_size = PAGE_SIZE; - } else { - roundedup = ((PAGE_SIZE - 1) & ro->blksiz) ? - ((ro->blksiz + PAGE_SIZE) & ~(PAGE_SIZE -1)) : - ro->blksiz; - if (roundedup > inode->i_size) - read_size = inode->i_size; - else - read_size = roundedup; - - } - } else { - read_size = PAGE_SIZE; - } - if (!read_size) - read_size = PAGE_SIZE; + read_size = 524288; if (PageDirty(page)) orangefs_launder_page(page); diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index ed67f39fa7ce..e12aeb9623d6 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -239,10 +239,6 @@ struct orangefs_write_range { kgid_t gid; }; -struct orangefs_read_options { - ssize_t blksiz; -}; - extern struct orangefs_stats orangefs_stats; /* diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 9fc47c2e078d..9709cf22cab3 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -36,6 +36,13 @@ static int ovl_ccup_get(char *buf, const struct kernel_param *param) module_param_call(check_copy_up, ovl_ccup_set, ovl_ccup_get, NULL, 0644); MODULE_PARM_DESC(check_copy_up, "Obsolete; does nothing"); +static bool ovl_must_copy_xattr(const char *name) +{ + return !strcmp(name, XATTR_POSIX_ACL_ACCESS) || + !strcmp(name, XATTR_POSIX_ACL_DEFAULT) || + !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); +} + int ovl_copy_xattr(struct dentry *old, struct dentry *new) { ssize_t list_size, size, value_size = 0; @@ -107,8 +114,13 @@ retry: continue; /* Discard */ } error = vfs_setxattr(new, name, value, size, 0); - if (error) - break; + if (error) { + if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name)) + break; + + /* Ignore failure to copy unknown xattrs */ + error = 0; + } } kfree(value); out: diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8e57d5372b8f..279009dee366 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -42,7 +42,7 @@ int ovl_cleanup(struct inode *wdir, struct dentry *wdentry) return err; } -static struct dentry *ovl_lookup_temp(struct dentry *workdir) +struct dentry *ovl_lookup_temp(struct dentry *workdir) { struct dentry *temp; char name[20]; @@ -243,6 +243,9 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, ovl_dir_modified(dentry->d_parent, false); ovl_dentry_set_upper_alias(dentry); + ovl_dentry_update_reval(dentry, newdentry, + DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + if (!hardlink) { /* * ovl_obtain_alias() can be called after ovl_create_real() @@ -819,6 +822,28 @@ static bool ovl_pure_upper(struct dentry *dentry) !ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry)); } +static void ovl_drop_nlink(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + struct dentry *alias; + + /* Try to find another, hashed alias */ + spin_lock(&inode->i_lock); + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + if (alias != dentry && !d_unhashed(alias)) + break; + } + spin_unlock(&inode->i_lock); + + /* + * Changes to underlying layers may cause i_nlink to lose sync with + * reality. In this case prevent the link count from going to zero + * prematurely. + */ + if (inode->i_nlink > !!alias) + drop_nlink(inode); +} + static int ovl_do_remove(struct dentry *dentry, bool is_dir) { int err; @@ -856,7 +881,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) if (is_dir) clear_nlink(dentry->d_inode); else - drop_nlink(dentry->d_inode); + ovl_drop_nlink(dentry); } ovl_nlink_end(dentry); @@ -1201,7 +1226,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, if (new_is_dir) clear_nlink(d_inode(new)); else - drop_nlink(d_inode(new)); + ovl_drop_nlink(new); } ovl_dir_modified(old->d_parent, ovl_type_origin(old) || diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 6f54d70cef27..475c61f53f0f 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -308,29 +308,35 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, ovl_set_flag(OVL_UPPERDATA, inode); dentry = d_find_any_alias(inode); - if (!dentry) { - dentry = d_alloc_anon(inode->i_sb); - if (!dentry) - goto nomem; - oe = ovl_alloc_entry(lower ? 1 : 0); - if (!oe) - goto nomem; - - if (lower) { - oe->lowerstack->dentry = dget(lower); - oe->lowerstack->layer = lowerpath->layer; - } - dentry->d_fsdata = oe; - if (upper_alias) - ovl_dentry_set_upper_alias(dentry); + if (dentry) + goto out_iput; + + dentry = d_alloc_anon(inode->i_sb); + if (unlikely(!dentry)) + goto nomem; + oe = ovl_alloc_entry(lower ? 1 : 0); + if (!oe) + goto nomem; + + if (lower) { + oe->lowerstack->dentry = dget(lower); + oe->lowerstack->layer = lowerpath->layer; } + dentry->d_fsdata = oe; + if (upper_alias) + ovl_dentry_set_upper_alias(dentry); + + ovl_dentry_update_reval(dentry, upper, + DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); return d_instantiate_anon(dentry, inode); nomem: - iput(inode); dput(dentry); - return ERR_PTR(-ENOMEM); + dentry = ERR_PTR(-ENOMEM); +out_iput: + iput(inode); + return dentry; } /* Get the upper or lower dentry in stach whose on layer @idx */ diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 79e8994e3bc1..b0d42ece4d7c 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -79,6 +79,7 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) { bool samefs = ovl_same_fs(dentry->d_sb); unsigned int xinobits = ovl_xino_bits(dentry->d_sb); + unsigned int xinoshift = 64 - xinobits; if (samefs) { /* @@ -89,22 +90,22 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) stat->dev = dentry->d_sb->s_dev; return 0; } else if (xinobits) { - unsigned int shift = 64 - xinobits; /* * All inode numbers of underlying fs should not be using the * high xinobits, so we use high xinobits to partition the * overlay st_ino address space. The high bits holds the fsid - * (upper fsid is 0). This way overlay inode numbers are unique - * and all inodes use overlay st_dev. Inode numbers are also - * persistent for a given layer configuration. + * (upper fsid is 0). The lowest xinobit is reserved for mapping + * the non-peresistent inode numbers range in case of overflow. + * This way all overlay inode numbers are unique and use the + * overlay st_dev. */ - if (stat->ino >> shift) { - pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n", - dentry, stat->ino, xinobits); - } else { - stat->ino |= ((u64)fsid) << shift; + if (likely(!(stat->ino >> xinoshift))) { + stat->ino |= ((u64)fsid) << (xinoshift + 1); stat->dev = dentry->d_sb->s_dev; return 0; + } else if (ovl_xino_warn(dentry->d_sb)) { + pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n", + dentry, stat->ino, xinobits); } } @@ -504,7 +505,7 @@ static const struct address_space_operations ovl_aops = { /* * It is possible to stack overlayfs instance on top of another - * overlayfs instance as lower layer. We need to annonate the + * overlayfs instance as lower layer. We need to annotate the * stackable i_mutex locks according to stack level of the super * block instance. An overlayfs instance can never be in stack * depth 0 (there is always a real fs below it). An overlayfs @@ -561,27 +562,73 @@ static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode) #endif } -static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, - unsigned long ino, int fsid) +static void ovl_next_ino(struct inode *inode) +{ + struct ovl_fs *ofs = inode->i_sb->s_fs_info; + + inode->i_ino = atomic_long_inc_return(&ofs->last_ino); + if (unlikely(!inode->i_ino)) + inode->i_ino = atomic_long_inc_return(&ofs->last_ino); +} + +static void ovl_map_ino(struct inode *inode, unsigned long ino, int fsid) { int xinobits = ovl_xino_bits(inode->i_sb); + unsigned int xinoshift = 64 - xinobits; /* * When d_ino is consistent with st_ino (samefs or i_ino has enough * bits to encode layer), set the same value used for st_ino to i_ino, * so inode number exposed via /proc/locks and a like will be * consistent with d_ino and st_ino values. An i_ino value inconsistent - * with d_ino also causes nfsd readdirplus to fail. When called from - * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real - * upper inode i_ino on ovl_inode_init() or ovl_inode_update(). + * with d_ino also causes nfsd readdirplus to fail. */ - if (ovl_same_dev(inode->i_sb)) { - inode->i_ino = ino; - if (xinobits && fsid && !(ino >> (64 - xinobits))) - inode->i_ino |= (unsigned long)fsid << (64 - xinobits); - } else { - inode->i_ino = get_next_ino(); + inode->i_ino = ino; + if (ovl_same_fs(inode->i_sb)) { + return; + } else if (xinobits && likely(!(ino >> xinoshift))) { + inode->i_ino |= (unsigned long)fsid << (xinoshift + 1); + return; + } + + /* + * For directory inodes on non-samefs with xino disabled or xino + * overflow, we allocate a non-persistent inode number, to be used for + * resolving st_ino collisions in ovl_map_dev_ino(). + * + * To avoid ino collision with legitimate xino values from upper + * layer (fsid 0), use the lowest xinobit to map the non + * persistent inode numbers to the unified st_ino address space. + */ + if (S_ISDIR(inode->i_mode)) { + ovl_next_ino(inode); + if (xinobits) { + inode->i_ino &= ~0UL >> xinobits; + inode->i_ino |= 1UL << xinoshift; + } } +} + +void ovl_inode_init(struct inode *inode, struct ovl_inode_params *oip, + unsigned long ino, int fsid) +{ + struct inode *realinode; + + if (oip->upperdentry) + OVL_I(inode)->__upperdentry = oip->upperdentry; + if (oip->lowerpath && oip->lowerpath->dentry) + OVL_I(inode)->lower = igrab(d_inode(oip->lowerpath->dentry)); + if (oip->lowerdata) + OVL_I(inode)->lowerdata = igrab(d_inode(oip->lowerdata)); + + realinode = ovl_inode_real(inode); + ovl_copyattr(realinode, inode); + ovl_copyflags(realinode, inode); + ovl_map_ino(inode, ino, fsid); +} + +static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev) +{ inode->i_mode = mode; inode->i_flags |= S_NOCMTIME; #ifdef CONFIG_FS_POSIX_ACL @@ -719,7 +766,7 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev) inode = new_inode(sb); if (inode) - ovl_fill_inode(inode, mode, rdev, 0, 0); + ovl_fill_inode(inode, mode, rdev); return inode; } @@ -891,7 +938,7 @@ struct inode *ovl_get_inode(struct super_block *sb, struct dentry *lowerdentry = lowerpath ? lowerpath->dentry : NULL; bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, oip->index); - int fsid = bylower ? oip->lowerpath->layer->fsid : 0; + int fsid = bylower ? lowerpath->layer->fsid : 0; bool is_dir, metacopy = false; unsigned long ino = 0; int err = oip->newinode ? -EEXIST : -ENOMEM; @@ -941,9 +988,11 @@ struct inode *ovl_get_inode(struct super_block *sb, err = -ENOMEM; goto out_err; } + ino = realinode->i_ino; + fsid = lowerpath->layer->fsid; } - ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev, ino, fsid); - ovl_inode_init(inode, upperdentry, lowerdentry, oip->lowerdata); + ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev); + ovl_inode_init(inode, oip, ino, fsid); if (upperdentry && ovl_is_impuredir(upperdentry)) ovl_set_flag(OVL_IMPURE, inode); diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index ed9e129fae04..0db23baf98e7 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -845,7 +845,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (err) goto out; - if (upperdentry && unlikely(ovl_dentry_remote(upperdentry))) { + if (upperdentry && upperdentry->d_flags & DCACHE_OP_REAL) { dput(upperdentry); err = -EREMOTE; goto out; @@ -1076,6 +1076,9 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, goto out_free_oe; } + ovl_dentry_update_reval(dentry, upperdentry, + DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + revert_creds(old_cred); if (origin_path) { dput(origin_path->dentry); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 3d3f2b8bdae5..e6f3670146ed 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -48,6 +48,12 @@ enum ovl_entry_flag { OVL_E_CONNECTED, }; +enum { + OVL_XINO_OFF, + OVL_XINO_AUTO, + OVL_XINO_ON, +}; + /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, * where: @@ -87,7 +93,7 @@ struct ovl_fb { u8 flags; /* OVL_FH_FLAG_* */ u8 type; /* fid_type of fid */ uuid_t uuid; /* uuid of filesystem */ - u32 fid[0]; /* file identifier should be 32bit aligned in-memory */ + u32 fid[]; /* file identifier should be 32bit aligned in-memory */ } __packed; /* In-memory and on-wire format for overlay file handle */ @@ -230,6 +236,8 @@ bool ovl_index_all(struct super_block *sb); bool ovl_verify_lower(struct super_block *sb); struct ovl_entry *ovl_alloc_entry(unsigned int numlower); bool ovl_dentry_remote(struct dentry *dentry); +void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *upperdentry, + unsigned int mask); bool ovl_dentry_weird(struct dentry *dentry); enum ovl_path_type ovl_path_type(struct dentry *dentry); void ovl_path_upper(struct dentry *dentry, struct path *path); @@ -264,8 +272,6 @@ void ovl_set_upperdata(struct inode *inode); bool ovl_redirect_dir(struct super_block *sb); const char *ovl_dentry_get_redirect(struct dentry *dentry); void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect); -void ovl_inode_init(struct inode *inode, struct dentry *upperdentry, - struct dentry *lowerdentry, struct dentry *lowerdata); void ovl_inode_update(struct inode *inode, struct dentry *upperdentry); void ovl_dir_modified(struct dentry *dentry, bool impurity); u64 ovl_dentry_version_get(struct dentry *dentry); @@ -301,6 +307,16 @@ static inline bool ovl_is_impuredir(struct dentry *dentry) return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE); } +/* + * With xino=auto, we do best effort to keep all inodes on same st_dev and + * d_ino consistent with st_ino. + * With xino=on, we do the same effort but we warn if we failed. + */ +static inline bool ovl_xino_warn(struct super_block *sb) +{ + return OVL_FS(sb)->config.xino == OVL_XINO_ON; +} + /* All layers on same fs? */ static inline bool ovl_same_fs(struct super_block *sb) { @@ -410,6 +426,8 @@ struct ovl_inode_params { char *redirect; struct dentry *lowerdata; }; +void ovl_inode_init(struct inode *inode, struct ovl_inode_params *oip, + unsigned long ino, int fsid); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, bool is_upper); @@ -451,6 +469,7 @@ struct ovl_cattr { struct dentry *ovl_create_real(struct inode *dir, struct dentry *newdentry, struct ovl_cattr *attr); int ovl_cleanup(struct inode *dir, struct dentry *dentry); +struct dentry *ovl_lookup_temp(struct dentry *workdir); struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr); /* file.c */ diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 89015ea822e7..5762d802fe01 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -75,6 +75,8 @@ struct ovl_fs { struct inode *indexdir_trap; /* -1: disabled, 0: same fs, 1..32: number of unused ino bits */ int xino_mode; + /* For allocation of non-persistent inode numbers */ + atomic_long_t last_ino; }; static inline struct ovl_fs *OVL_FS(struct super_block *sb) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 40ac9ce2465a..e452ff7d583d 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -438,15 +438,23 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) /* Map inode number to lower fs unique range */ static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid, - const char *name, int namelen) + const char *name, int namelen, bool warn) { - if (ino >> (64 - xinobits)) { - pr_warn_ratelimited("d_ino too big (%.*s, ino=%llu, xinobits=%d)\n", - namelen, name, ino, xinobits); + unsigned int xinoshift = 64 - xinobits; + + if (unlikely(ino >> xinoshift)) { + if (warn) { + pr_warn_ratelimited("d_ino too big (%.*s, ino=%llu, xinobits=%d)\n", + namelen, name, ino, xinobits); + } return ino; } - return ino | ((u64)fsid) << (64 - xinobits); + /* + * The lowest xinobit is reserved for mapping the non-peresistent inode + * numbers range, but this range is only exposed via st_ino, not here. + */ + return ino | ((u64)fsid) << (xinoshift + 1); } /* @@ -515,7 +523,8 @@ get: } else if (xinobits && !OVL_TYPE_UPPER(type)) { ino = ovl_remap_lower_ino(ino, xinobits, ovl_layer_lower(this)->fsid, - p->name, p->len); + p->name, p->len, + ovl_xino_warn(dir->d_sb)); } out: @@ -645,6 +654,7 @@ struct ovl_readdir_translate { u64 parent_ino; int fsid; int xinobits; + bool xinowarn; }; static int ovl_fill_real(struct dir_context *ctx, const char *name, @@ -665,7 +675,7 @@ static int ovl_fill_real(struct dir_context *ctx, const char *name, ino = p->ino; } else if (rdt->xinobits) { ino = ovl_remap_lower_ino(ino, rdt->xinobits, rdt->fsid, - name, namelen); + name, namelen, rdt->xinowarn); } return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type); @@ -696,6 +706,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) .ctx.actor = ovl_fill_real, .orig_ctx = ctx, .xinobits = ovl_xino_bits(dir->d_sb), + .xinowarn = ovl_xino_warn(dir->d_sb), }; if (rdt.xinobits && lower_layer) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index ac967f1cb6e5..732ad5495c92 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -113,53 +113,54 @@ bug: return dentry; } -static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak) { - struct ovl_entry *oe = dentry->d_fsdata; - unsigned int i; int ret = 1; - for (i = 0; i < oe->numlower; i++) { - struct dentry *d = oe->lowerstack[i].dentry; - - if (d->d_flags & DCACHE_OP_REVALIDATE) { - ret = d->d_op->d_revalidate(d, flags); - if (ret < 0) - return ret; - if (!ret) { - if (!(flags & LOOKUP_RCU)) - d_invalidate(d); - return -ESTALE; - } + if (weak) { + if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) + ret = d->d_op->d_weak_revalidate(d, flags); + } else if (d->d_flags & DCACHE_OP_REVALIDATE) { + ret = d->d_op->d_revalidate(d, flags); + if (!ret) { + if (!(flags & LOOKUP_RCU)) + d_invalidate(d); + ret = -ESTALE; } } - return 1; + return ret; } -static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags) +static int ovl_dentry_revalidate_common(struct dentry *dentry, + unsigned int flags, bool weak) { struct ovl_entry *oe = dentry->d_fsdata; + struct dentry *upper; unsigned int i; int ret = 1; - for (i = 0; i < oe->numlower; i++) { - struct dentry *d = oe->lowerstack[i].dentry; + upper = ovl_dentry_upper(dentry); + if (upper) + ret = ovl_revalidate_real(upper, flags, weak); - if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) { - ret = d->d_op->d_weak_revalidate(d, flags); - if (ret <= 0) - break; - } + for (i = 0; ret > 0 && i < oe->numlower; i++) { + ret = ovl_revalidate_real(oe->lowerstack[i].dentry, flags, + weak); } return ret; } -static const struct dentry_operations ovl_dentry_operations = { - .d_release = ovl_dentry_release, - .d_real = ovl_d_real, -}; +static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags) +{ + return ovl_dentry_revalidate_common(dentry, flags, false); +} + +static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags) +{ + return ovl_dentry_revalidate_common(dentry, flags, true); +} -static const struct dentry_operations ovl_reval_dentry_operations = { +static const struct dentry_operations ovl_dentry_operations = { .d_release = ovl_dentry_release, .d_real = ovl_d_real, .d_revalidate = ovl_dentry_revalidate, @@ -316,12 +317,6 @@ static const char *ovl_redirect_mode_def(void) return ovl_redirect_dir_def ? "on" : "off"; } -enum { - OVL_XINO_OFF, - OVL_XINO_AUTO, - OVL_XINO_ON, -}; - static const char * const ovl_xino_str[] = { "off", "auto", @@ -751,13 +746,12 @@ static int ovl_mount_dir(const char *name, struct path *path) ovl_unescape(tmp); err = ovl_mount_dir_noesc(tmp, path); - if (!err) - if (ovl_dentry_remote(path->dentry)) { - pr_err("filesystem on '%s' not supported as upperdir\n", - tmp); - path_put_init(path); - err = -EINVAL; - } + if (!err && path->dentry->d_flags & DCACHE_OP_REAL) { + pr_err("filesystem on '%s' not supported as upperdir\n", + tmp); + path_put_init(path); + err = -EINVAL; + } kfree(tmp); } return err; @@ -778,7 +772,7 @@ static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs, } static int ovl_lower_dir(const char *name, struct path *path, - struct ovl_fs *ofs, int *stack_depth, bool *remote) + struct ovl_fs *ofs, int *stack_depth) { int fh_type; int err; @@ -793,9 +787,6 @@ static int ovl_lower_dir(const char *name, struct path *path, *stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth); - if (ovl_dentry_remote(path->dentry)) - *remote = true; - /* * The inodes index feature and NFS export need to encode and decode * file handles, so they require that all layers support them. @@ -1074,11 +1065,73 @@ out: return err; } +/* + * Returns 1 if RENAME_WHITEOUT is supported, 0 if not supported and + * negative values if error is encountered. + */ +static int ovl_check_rename_whiteout(struct dentry *workdir) +{ + struct inode *dir = d_inode(workdir); + struct dentry *temp; + struct dentry *dest; + struct dentry *whiteout; + struct name_snapshot name; + int err; + + inode_lock_nested(dir, I_MUTEX_PARENT); + + temp = ovl_create_temp(workdir, OVL_CATTR(S_IFREG | 0)); + err = PTR_ERR(temp); + if (IS_ERR(temp)) + goto out_unlock; + + dest = ovl_lookup_temp(workdir); + err = PTR_ERR(dest); + if (IS_ERR(dest)) { + dput(temp); + goto out_unlock; + } + + /* Name is inline and stable - using snapshot as a copy helper */ + take_dentry_name_snapshot(&name, temp); + err = ovl_do_rename(dir, temp, dir, dest, RENAME_WHITEOUT); + if (err) { + if (err == -EINVAL) + err = 0; + goto cleanup_temp; + } + + whiteout = lookup_one_len(name.name.name, workdir, name.name.len); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + goto cleanup_temp; + + err = ovl_is_whiteout(whiteout); + + /* Best effort cleanup of whiteout and temp file */ + if (err) + ovl_cleanup(dir, whiteout); + dput(whiteout); + +cleanup_temp: + ovl_cleanup(dir, temp); + release_dentry_name_snapshot(&name); + dput(temp); + dput(dest); + +out_unlock: + inode_unlock(dir); + + return err; +} + static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, struct path *workpath) { struct vfsmount *mnt = ofs->upper_mnt; struct dentry *temp; + bool rename_whiteout; + bool d_type; int fh_type; int err; @@ -1104,11 +1157,8 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, if (err < 0) goto out; - /* - * We allowed this configuration and don't want to break users over - * kernel upgrade. So warn instead of erroring out. - */ - if (!err) + d_type = err; + if (!d_type) pr_warn("upper fs needs to support d_type.\n"); /* Check if upper/work fs supports O_TMPFILE */ @@ -1119,6 +1169,16 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, else pr_warn("upper fs does not support tmpfile.\n"); + + /* Check if upper/work fs supports RENAME_WHITEOUT */ + err = ovl_check_rename_whiteout(ofs->workdir); + if (err < 0) + goto out; + + rename_whiteout = err; + if (!rename_whiteout) + pr_warn("upper fs does not support RENAME_WHITEOUT.\n"); + /* * Check if upper/work fs supports trusted.overlay.* xattr */ @@ -1133,6 +1193,18 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE); } + /* + * We allowed sub-optimal upper fs configuration and don't want to break + * users over kernel upgrade, but we never allowed remote upper fs, so + * we can enforce strict requirements for remote upper fs. + */ + if (ovl_dentry_remote(ofs->workdir) && + (!d_type || !rename_whiteout || ofs->noxattr)) { + pr_err("upper fs missing required features.\n"); + err = -EINVAL; + goto out; + } + /* Check if upper/work fs supports file handles */ fh_type = ovl_can_decode_fh(ofs->workdir->d_sb); if (ofs->config.index && !fh_type) { @@ -1401,11 +1473,12 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, /* * When all layers on same fs, overlay can use real inode numbers. - * With mount option "xino=on", mounter declares that there are enough - * free high bits in underlying fs to hold the unique fsid. + * With mount option "xino=<on|auto>", mounter declares that there are + * enough free high bits in underlying fs to hold the unique fsid. * If overlayfs does encounter underlying inodes using the high xino * bits reserved for fsid, it emits a warning and uses the original - * inode number. + * inode number or a non persistent inode number allocated from a + * dedicated range. */ if (ofs->numfs - !ofs->upper_mnt == 1) { if (ofs->config.xino == OVL_XINO_ON) @@ -1413,14 +1486,16 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, ofs->xino_mode = 0; } else if (ofs->config.xino == OVL_XINO_OFF) { ofs->xino_mode = -1; - } else if (ofs->config.xino == OVL_XINO_ON && ofs->xino_mode < 0) { + } else if (ofs->xino_mode < 0) { /* * This is a roundup of number of bits needed for encoding - * fsid, where fsid 0 is reserved for upper fs even with - * lower only overlay. + * fsid, where fsid 0 is reserved for upper fs (even with + * lower only overlay) +1 extra bit is reserved for the non + * persistent inode number range that is used for resolving + * xino lower bits overflow. */ - BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31); - ofs->xino_mode = ilog2(ofs->numfs - 1) + 1; + BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 30); + ofs->xino_mode = ilog2(ofs->numfs - 1) + 2; } if (ofs->xino_mode > 0) { @@ -1440,7 +1515,6 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, char *lowertmp, *lower; struct path *stack = NULL; unsigned int stacklen, numlower = 0, i; - bool remote = false; struct ovl_entry *oe; err = -ENOMEM; @@ -1472,7 +1546,7 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, lower = lowertmp; for (numlower = 0; numlower < stacklen; numlower++) { err = ovl_lower_dir(lower, &stack[numlower], ofs, - &sb->s_stack_depth, &remote); + &sb->s_stack_depth); if (err) goto out_err; @@ -1500,11 +1574,6 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, oe->lowerstack[i].layer = &ofs->layers[i+1]; } - if (remote) - sb->s_d_op = &ovl_reval_dentry_operations; - else - sb->s_d_op = &ovl_dentry_operations; - out: for (i = 0; i < numlower; i++) path_put(&stack[i]); @@ -1589,6 +1658,44 @@ static int ovl_check_overlapping_layers(struct super_block *sb, return 0; } +static struct dentry *ovl_get_root(struct super_block *sb, + struct dentry *upperdentry, + struct ovl_entry *oe) +{ + struct dentry *root; + struct ovl_path *lowerpath = &oe->lowerstack[0]; + unsigned long ino = d_inode(lowerpath->dentry)->i_ino; + int fsid = lowerpath->layer->fsid; + struct ovl_inode_params oip = { + .upperdentry = upperdentry, + .lowerpath = lowerpath, + }; + + root = d_make_root(ovl_new_inode(sb, S_IFDIR, 0)); + if (!root) + return NULL; + + root->d_fsdata = oe; + + if (upperdentry) { + /* Root inode uses upper st_ino/i_ino */ + ino = d_inode(upperdentry)->i_ino; + fsid = 0; + ovl_dentry_set_upper_alias(root); + if (ovl_is_impuredir(upperdentry)) + ovl_set_flag(OVL_IMPURE, d_inode(root)); + } + + /* Root is always merge -> can have whiteouts */ + ovl_set_flag(OVL_WHITEOUTS, d_inode(root)); + ovl_dentry_set_flag(OVL_E_CONNECTED, root); + ovl_set_upperdata(d_inode(root)); + ovl_inode_init(d_inode(root), &oip, ino, fsid); + ovl_dentry_update_reval(root, upperdentry, DCACHE_OP_WEAK_REVALIDATE); + + return root; +} + static int ovl_fill_super(struct super_block *sb, void *data, int silent) { struct path upperpath = { }; @@ -1598,6 +1705,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) struct cred *cred; int err; + sb->s_d_op = &ovl_dentry_operations; + err = -ENOMEM; ofs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); if (!ofs) @@ -1624,6 +1733,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_stack_depth = 0; sb->s_maxbytes = MAX_LFS_FILESIZE; + atomic_long_set(&ofs->last_ino, 1); /* Assume underlaying fs uses 32bit inodes unless proven otherwise */ if (ofs->config.xino != OVL_XINO_OFF) { ofs->xino_mode = BITS_PER_LONG - 32; @@ -1710,25 +1820,11 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= SB_POSIXACL; err = -ENOMEM; - root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0)); + root_dentry = ovl_get_root(sb, upperpath.dentry, oe); if (!root_dentry) goto out_free_oe; - root_dentry->d_fsdata = oe; - mntput(upperpath.mnt); - if (upperpath.dentry) { - ovl_dentry_set_upper_alias(root_dentry); - if (ovl_is_impuredir(upperpath.dentry)) - ovl_set_flag(OVL_IMPURE, d_inode(root_dentry)); - } - - /* Root is always merge -> can have whiteouts */ - ovl_set_flag(OVL_WHITEOUTS, d_inode(root_dentry)); - ovl_dentry_set_flag(OVL_E_CONNECTED, root_dentry); - ovl_set_upperdata(d_inode(root_dentry)); - ovl_inode_init(d_inode(root_dentry), upperpath.dentry, - ovl_dentry_lower(root_dentry), NULL); sb->s_root = root_dentry; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 042f7eb4f7f4..36b60788ee47 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -93,8 +93,24 @@ struct ovl_entry *ovl_alloc_entry(unsigned int numlower) bool ovl_dentry_remote(struct dentry *dentry) { return dentry->d_flags & - (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | - DCACHE_OP_REAL); + (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); +} + +void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *upperdentry, + unsigned int mask) +{ + struct ovl_entry *oe = OVL_E(dentry); + unsigned int i, flags = 0; + + if (upperdentry) + flags |= upperdentry->d_flags; + for (i = 0; i < oe->numlower; i++) + flags |= oe->lowerstack[i].dentry->d_flags; + + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~mask; + dentry->d_flags |= flags & mask; + spin_unlock(&dentry->d_lock); } bool ovl_dentry_weird(struct dentry *dentry) @@ -386,24 +402,6 @@ void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect) oi->redirect = redirect; } -void ovl_inode_init(struct inode *inode, struct dentry *upperdentry, - struct dentry *lowerdentry, struct dentry *lowerdata) -{ - struct inode *realinode = d_inode(upperdentry ?: lowerdentry); - - if (upperdentry) - OVL_I(inode)->__upperdentry = upperdentry; - if (lowerdentry) - OVL_I(inode)->lower = igrab(d_inode(lowerdentry)); - if (lowerdata) - OVL_I(inode)->lowerdata = igrab(d_inode(lowerdata)); - - ovl_copyattr(realinode, inode); - ovl_copyflags(realinode, inode); - if (!inode->i_ino) - inode->i_ino = realinode->i_ino; -} - void ovl_inode_update(struct inode *inode, struct dentry *upperdentry) { struct inode *upperinode = d_inode(upperdentry); @@ -416,8 +414,6 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry) smp_wmb(); OVL_I(inode)->__upperdentry = upperdentry; if (inode_unhashed(inode)) { - if (!inode->i_ino) - inode->i_ino = upperinode->i_ino; inode->i_private = upperinode; __insert_inode_hash(inode, (unsigned long) upperinode); } diff --git a/fs/proc/base.c b/fs/proc/base.c index 74f948a6b621..6042b646ab27 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1839,9 +1839,9 @@ void proc_pid_evict_inode(struct proc_inode *ei) struct pid *pid = ei->pid; if (S_ISDIR(ei->vfs_inode.i_mode)) { - spin_lock(&pid->wait_pidfd.lock); + spin_lock(&pid->lock); hlist_del_init_rcu(&ei->sibling_inodes); - spin_unlock(&pid->wait_pidfd.lock); + spin_unlock(&pid->lock); } put_pid(pid); @@ -1877,9 +1877,9 @@ struct inode *proc_pid_make_inode(struct super_block * sb, /* Let the pid remember us for quick removal */ ei->pid = pid; if (S_ISDIR(mode)) { - spin_lock(&pid->wait_pidfd.lock); + spin_lock(&pid->lock); hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); - spin_unlock(&pid->wait_pidfd.lock); + spin_unlock(&pid->lock); } task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); @@ -3273,7 +3273,7 @@ static const struct inode_operations proc_tgid_base_inode_operations = { void proc_flush_pid(struct pid *pid) { - proc_invalidate_siblings_dcache(&pid->inodes, &pid->wait_pidfd.lock); + proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); put_pid(pid); } diff --git a/fs/read_write.c b/fs/read_write.c index 59d819c5b92e..bbfa9b12b15e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -331,7 +331,8 @@ COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned i } #endif -#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) +#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ + defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) diff --git a/fs/seq_file.c b/fs/seq_file.c index 79781ebd2145..70f5fdf99bf6 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -232,9 +232,12 @@ Fill: loff_t pos = m->index; p = m->op->next(m, p, &m->index); - if (pos == m->index) - /* Buggy ->next function */ + if (pos == m->index) { + pr_info_ratelimited("buggy seq_file .next function %ps " + "did not updated position index\n", + m->op->next); m->index++; + } if (!p || IS_ERR(p)) { err = PTR_ERR(p); break; diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h index 3fd85464abd5..736ebc5dc441 100644 --- a/fs/udf/ecma_167.h +++ b/fs/udf/ecma_167.h @@ -5,7 +5,7 @@ * http://www.ecma.ch * * Copyright (c) 2001-2002 Ben Fennema - * Copyright (c) 2017-2019 Pali Rohár <pali.rohar@gmail.com> + * Copyright (c) 2017-2019 Pali Rohár <pali@kernel.org> * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h index 35e61b2cacfe..d5fbfab3ddb6 100644 --- a/fs/udf/osta_udf.h +++ b/fs/udf/osta_udf.h @@ -5,7 +5,7 @@ * http://www.osta.org * * Copyright (c) 2001-2004 Ben Fennema - * Copyright (c) 2017-2019 Pali Rohár <pali.rohar@gmail.com> + * Copyright (c) 2017-2019 Pali Rohár <pali@kernel.org> * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 00266de58954..c526c5e5ab76 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -328,6 +328,38 @@ xfs_validate_sb_common( return -EFSCORRUPTED; } + /* Validate the realtime geometry; stolen from xfs_repair */ + if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || + sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) { + xfs_notice(mp, + "realtime extent sanity check failed"); + return -EFSCORRUPTED; + } + + if (sbp->sb_rblocks == 0) { + if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 || + sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) { + xfs_notice(mp, + "realtime zeroed geometry check failed"); + return -EFSCORRUPTED; + } + } else { + uint64_t rexts; + uint64_t rbmblocks; + + rexts = div_u64(sbp->sb_rblocks, sbp->sb_rextsize); + rbmblocks = howmany_64(sbp->sb_rextents, + NBBY * sbp->sb_blocksize); + + if (sbp->sb_rextents != rexts || + sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) || + sbp->sb_rbmblocks != rbmblocks) { + xfs_notice(mp, + "realtime geometry sanity check failed"); + return -EFSCORRUPTED; + } + } + if (sbp->sb_unit) { if (!xfs_sb_version_hasdalign(sbp) || sbp->sb_unit > sbp->sb_width || diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index f880141a2268..9ec3eaf1c618 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -327,6 +327,9 @@ xfs_buf_free( __free_page(page); } + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += + bp->b_page_count; } else if (bp->b_flags & _XBF_KMEM) kmem_free(bp->b_addr); _xfs_buf_free_pages(bp); @@ -2114,9 +2117,11 @@ xfs_buf_delwri_pushbuf( int __init xfs_buf_init(void) { - xfs_buf_zone = kmem_cache_create("xfs_buf", - sizeof(struct xfs_buf), 0, - SLAB_HWCACHE_ALIGN, NULL); + xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, + SLAB_HWCACHE_ALIGN | + SLAB_RECLAIM_ACCOUNT | + SLAB_MEM_SPREAD, + NULL); if (!xfs_buf_zone) goto out; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 711376ca269f..af2c8e5ceea0 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1105,8 +1105,8 @@ xfs_qm_dqflush( * Get the buffer containing the on-disk dquot */ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, 0, &bp, - &xfs_dquot_buf_ops); + mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK, + &bp, &xfs_dquot_buf_ops); if (error) goto out_unlock; @@ -1177,7 +1177,7 @@ xfs_qm_dqflush( out_unlock: xfs_dqfunlock(dqp); - return -EIO; + return error; } /* diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index cf65e2e43c6e..baad1748d0d1 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -189,7 +189,8 @@ xfs_qm_dquot_logitem_push( if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; xfs_buf_relse(bp); - } + } else if (error == -EAGAIN) + rval = XFS_ITEM_LOCKED; spin_lock(&lip->li_ailp->ail_lock); out_unlock: diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index f1372f9046e3..5a4b0119143a 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -15,7 +15,6 @@ #include "xfs_trans.h" #include "xfs_inode_item.h" #include "xfs_icache.h" -#include "xfs_log.h" #include "xfs_pnfs.h" /* @@ -221,18 +220,7 @@ STATIC int xfs_fs_nfs_commit_metadata( struct inode *inode) { - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - xfs_lsn_t lsn = 0; - - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) - lsn = ip->i_itemp->ili_last_lsn; - xfs_iunlock(ip, XFS_ILOCK_SHARED); - - if (!lsn) - return 0; - return xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL); + return xfs_log_force_inode(XFS_I(inode)); } const struct export_operations xfs_export_operations = { diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index b8a4a3f29b36..4b8bdecc3863 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -80,19 +80,9 @@ xfs_dir_fsync( int datasync) { struct xfs_inode *ip = XFS_I(file->f_mapping->host); - struct xfs_mount *mp = ip->i_mount; - xfs_lsn_t lsn = 0; trace_xfs_dir_fsync(ip); - - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) - lsn = ip->i_itemp->ili_last_lsn; - xfs_iunlock(ip, XFS_ILOCK_SHARED); - - if (!lsn) - return 0; - return xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL); + return xfs_log_force_inode(ip); } STATIC int @@ -1069,7 +1059,11 @@ xfs_file_remap_range( ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, remap_flags); + if (ret) + goto out_unlock; + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_log_force_inode(dest); out_unlock: xfs_reflink_remap_unlock(file_in, file_out); if (ret) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 14b922f2a6db..d1772786af29 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1200,8 +1200,7 @@ xfs_create( unlock_dp_on_error = false; error = xfs_dir_createname(tp, dp, name, ip->i_ino, - resblks ? - resblks - XFS_IALLOC_SPACE_RES(mp) : 0); + resblks - XFS_IALLOC_SPACE_RES(mp)); if (error) { ASSERT(error != -ENOSPC); goto out_trans_cancel; @@ -2504,6 +2503,88 @@ out: } /* + * Look up the inode number specified and mark it stale if it is found. If it is + * dirty, return the inode so it can be attached to the cluster buffer so it can + * be processed appropriately when the cluster free transaction completes. + */ +static struct xfs_inode * +xfs_ifree_get_one_inode( + struct xfs_perag *pag, + struct xfs_inode *free_ip, + xfs_ino_t inum) +{ + struct xfs_mount *mp = pag->pag_mount; + struct xfs_inode *ip; + +retry: + rcu_read_lock(); + ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum)); + + /* Inode not in memory, nothing to do */ + if (!ip) + goto out_rcu_unlock; + + /* + * because this is an RCU protected lookup, we could find a recently + * freed or even reallocated inode during the lookup. We need to check + * under the i_flags_lock for a valid inode here. Skip it if it is not + * valid, the wrong inode or stale. + */ + spin_lock(&ip->i_flags_lock); + if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) { + spin_unlock(&ip->i_flags_lock); + goto out_rcu_unlock; + } + spin_unlock(&ip->i_flags_lock); + + /* + * Don't try to lock/unlock the current inode, but we _cannot_ skip the + * other inodes that we did not find in the list attached to the buffer + * and are not already marked stale. If we can't lock it, back off and + * retry. + */ + if (ip != free_ip) { + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { + rcu_read_unlock(); + delay(1); + goto retry; + } + + /* + * Check the inode number again in case we're racing with + * freeing in xfs_reclaim_inode(). See the comments in that + * function for more information as to why the initial check is + * not sufficient. + */ + if (ip->i_ino != inum) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); + goto out_rcu_unlock; + } + } + rcu_read_unlock(); + + xfs_iflock(ip); + xfs_iflags_set(ip, XFS_ISTALE); + + /* + * We don't need to attach clean inodes or those only with unlogged + * changes (which we throw away, anyway). + */ + if (!ip->i_itemp || xfs_inode_clean(ip)) { + ASSERT(ip != free_ip); + xfs_ifunlock(ip); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + goto out_no_inode; + } + return ip; + +out_rcu_unlock: + rcu_read_unlock(); +out_no_inode: + return NULL; +} + +/* * A big issue when freeing the inode cluster is that we _cannot_ skip any * inodes that are in memory - they all must be marked stale and attached to * the cluster buffer. @@ -2603,77 +2684,11 @@ xfs_ifree_cluster( * even trying to lock them. */ for (i = 0; i < igeo->inodes_per_cluster; i++) { -retry: - rcu_read_lock(); - ip = radix_tree_lookup(&pag->pag_ici_root, - XFS_INO_TO_AGINO(mp, (inum + i))); - - /* Inode not in memory, nothing to do */ - if (!ip) { - rcu_read_unlock(); + ip = xfs_ifree_get_one_inode(pag, free_ip, inum + i); + if (!ip) continue; - } - - /* - * because this is an RCU protected lookup, we could - * find a recently freed or even reallocated inode - * during the lookup. We need to check under the - * i_flags_lock for a valid inode here. Skip it if it - * is not valid, the wrong inode or stale. - */ - spin_lock(&ip->i_flags_lock); - if (ip->i_ino != inum + i || - __xfs_iflags_test(ip, XFS_ISTALE)) { - spin_unlock(&ip->i_flags_lock); - rcu_read_unlock(); - continue; - } - spin_unlock(&ip->i_flags_lock); - - /* - * Don't try to lock/unlock the current inode, but we - * _cannot_ skip the other inodes that we did not find - * in the list attached to the buffer and are not - * already marked stale. If we can't lock it, back off - * and retry. - */ - if (ip != free_ip) { - if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { - rcu_read_unlock(); - delay(1); - goto retry; - } - - /* - * Check the inode number again in case we're - * racing with freeing in xfs_reclaim_inode(). - * See the comments in that function for more - * information as to why the initial check is - * not sufficient. - */ - if (ip->i_ino != inum + i) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - rcu_read_unlock(); - continue; - } - } - rcu_read_unlock(); - - xfs_iflock(ip); - xfs_iflags_set(ip, XFS_ISTALE); - /* - * we don't need to attach clean inodes or those only - * with unlogged changes (which we throw away, anyway). - */ iip = ip->i_itemp; - if (!iip || xfs_inode_clean(ip)) { - ASSERT(ip != free_ip); - xfs_ifunlock(ip); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - continue; - } - iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; iip->ili_fsync_fields = 0; @@ -3930,3 +3945,22 @@ xfs_irele( trace_xfs_irele(ip, _RET_IP_); iput(VFS_I(ip)); } + +/* + * Ensure all commited transactions touching the inode are written to the log. + */ +int +xfs_log_force_inode( + struct xfs_inode *ip) +{ + xfs_lsn_t lsn = 0; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + if (xfs_ipincount(ip)) + lsn = ip->i_itemp->ili_last_lsn; + xfs_iunlock(ip, XFS_ILOCK_SHARED); + + if (!lsn) + return 0; + return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL); +} diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 492e53992fa9..c6a63f6764a6 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -426,6 +426,7 @@ int xfs_itruncate_extents_flags(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t, int); void xfs_iext_realloc(xfs_inode_t *, int, int); +int xfs_log_force_inode(struct xfs_inode *ip); void xfs_iunpin_wait(xfs_inode_t *); #define xfs_ipincount(ip) ((unsigned int) atomic_read(&ip->i_pincount)) diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 4a3d13d4a022..f779cca2346f 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -552,7 +552,8 @@ xfs_inode_item_push( if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; xfs_buf_relse(bp); - } + } else if (error == -EAGAIN) + rval = XFS_ITEM_LOCKED; spin_lock(&lip->li_ailp->ail_lock); out_unlock: @@ -730,29 +731,27 @@ xfs_iflush_done( * holding the lock before removing the inode from the AIL. */ if (need_ail) { - bool mlip_changed = false; + xfs_lsn_t tail_lsn = 0; /* this is an opencoded batch version of xfs_trans_ail_delete */ spin_lock(&ailp->ail_lock); list_for_each_entry(blip, &tmp, li_bio_list) { if (INODE_ITEM(blip)->ili_logged && - blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) - mlip_changed |= xfs_ail_delete_one(ailp, blip); - else { + blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) { + /* + * xfs_ail_update_finish() only cares about the + * lsn of the first tail item removed, any + * others will be at the same or higher lsn so + * we just ignore them. + */ + xfs_lsn_t lsn = xfs_ail_delete_one(ailp, blip); + if (!tail_lsn && lsn) + tail_lsn = lsn; + } else { xfs_clear_li_failed(blip); } } - - if (mlip_changed) { - if (!XFS_FORCED_SHUTDOWN(ailp->ail_mount)) - xlog_assign_tail_lsn_locked(ailp->ail_mount); - if (list_empty(&ailp->ail_head)) - wake_up_all(&ailp->ail_empty); - } - spin_unlock(&ailp->ail_lock); - - if (mlip_changed) - xfs_log_space_wake(ailp->ail_mount); + xfs_ail_update_finish(ailp, tail_lsn); } /* diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 4a53768c5397..00fda2e8e738 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -24,13 +24,6 @@ kmem_zone_t *xfs_log_ticket_zone; /* Local miscellaneous function prototypes */ -STATIC int -xlog_commit_record( - struct xlog *log, - struct xlog_ticket *ticket, - struct xlog_in_core **iclog, - xfs_lsn_t *commitlsnp); - STATIC struct xlog * xlog_alloc_log( struct xfs_mount *mp, @@ -66,14 +59,6 @@ xlog_grant_push_ail( struct xlog *log, int need_bytes); STATIC void -xlog_regrant_reserve_log_space( - struct xlog *log, - struct xlog_ticket *ticket); -STATIC void -xlog_ungrant_log_space( - struct xlog *log, - struct xlog_ticket *ticket); -STATIC void xlog_sync( struct xlog *log, struct xlog_in_core *iclog); @@ -478,73 +463,6 @@ out_error: return error; } - -/* - * NOTES: - * - * 1. currblock field gets updated at startup and after in-core logs - * marked as with WANT_SYNC. - */ - -/* - * This routine is called when a user of a log manager ticket is done with - * the reservation. If the ticket was ever used, then a commit record for - * the associated transaction is written out as a log operation header with - * no data. The flag XLOG_TIC_INITED is set when the first write occurs with - * a given ticket. If the ticket was one with a permanent reservation, then - * a few operations are done differently. Permanent reservation tickets by - * default don't release the reservation. They just commit the current - * transaction with the belief that the reservation is still needed. A flag - * must be passed in before permanent reservations are actually released. - * When these type of tickets are not released, they need to be set into - * the inited state again. By doing this, a start record will be written - * out when the next write occurs. - */ -xfs_lsn_t -xfs_log_done( - struct xfs_mount *mp, - struct xlog_ticket *ticket, - struct xlog_in_core **iclog, - bool regrant) -{ - struct xlog *log = mp->m_log; - xfs_lsn_t lsn = 0; - - if (XLOG_FORCED_SHUTDOWN(log) || - /* - * If nothing was ever written, don't write out commit record. - * If we get an error, just continue and give back the log ticket. - */ - (((ticket->t_flags & XLOG_TIC_INITED) == 0) && - (xlog_commit_record(log, ticket, iclog, &lsn)))) { - lsn = (xfs_lsn_t) -1; - regrant = false; - } - - - if (!regrant) { - trace_xfs_log_done_nonperm(log, ticket); - - /* - * Release ticket if not permanent reservation or a specific - * request has been made to release a permanent reservation. - */ - xlog_ungrant_log_space(log, ticket); - } else { - trace_xfs_log_done_perm(log, ticket); - - xlog_regrant_reserve_log_space(log, ticket); - /* If this ticket was a permanent reservation and we aren't - * trying to release it, reset the inited flags; so next time - * we write, a start record will be written out. - */ - ticket->t_flags |= XLOG_TIC_INITED; - } - - xfs_log_ticket_put(ticket); - return lsn; -} - static bool __xlog_state_release_iclog( struct xlog *log, @@ -869,32 +787,44 @@ xlog_wait_on_iclog( } /* - * Final log writes as part of unmount. - * - * Mark the filesystem clean as unmount happens. Note that during relocation - * this routine needs to be executed as part of source-bag while the - * deallocation must not be done until source-end. + * Write out an unmount record using the ticket provided. We have to account for + * the data space used in the unmount ticket as this write is not done from a + * transaction context that has already done the accounting for us. */ - -/* Actually write the unmount record to disk. */ -static void -xfs_log_write_unmount_record( - struct xfs_mount *mp) +static int +xlog_write_unmount_record( + struct xlog *log, + struct xlog_ticket *ticket, + xfs_lsn_t *lsn, + uint flags) { - /* the data section must be 32 bit size aligned */ - struct xfs_unmount_log_format magic = { + struct xfs_unmount_log_format ulf = { .magic = XLOG_UNMOUNT_TYPE, }; struct xfs_log_iovec reg = { - .i_addr = &magic, - .i_len = sizeof(magic), + .i_addr = &ulf, + .i_len = sizeof(ulf), .i_type = XLOG_REG_TYPE_UNMOUNT, }; struct xfs_log_vec vec = { .lv_niovecs = 1, .lv_iovecp = ®, }; - struct xlog *log = mp->m_log; + + /* account for space used by record data */ + ticket->t_curr_res -= sizeof(ulf); + return xlog_write(log, &vec, ticket, lsn, NULL, flags, false); +} + +/* + * Mark the filesystem clean by writing an unmount record to the head of the + * log. + */ +static void +xlog_unmount_write( + struct xlog *log) +{ + struct xfs_mount *mp = log->l_mp; struct xlog_in_core *iclog; struct xlog_ticket *tic = NULL; xfs_lsn_t lsn; @@ -905,23 +835,7 @@ xfs_log_write_unmount_record( if (error) goto out_err; - /* - * If we think the summary counters are bad, clear the unmount header - * flag in the unmount record so that the summary counters will be - * recalculated during log recovery at next mount. Refer to - * xlog_check_unmount_rec for more details. - */ - if (XFS_TEST_ERROR(xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS), mp, - XFS_ERRTAG_FORCE_SUMMARY_RECALC)) { - xfs_alert(mp, "%s: will fix summary counters at next mount", - __func__); - flags &= ~XLOG_UNMOUNT_TRANS; - } - - /* remove inited flag, and account for space used */ - tic->t_flags = 0; - tic->t_curr_res -= sizeof(magic); - error = xlog_write(log, &vec, tic, &lsn, NULL, flags); + error = xlog_write_unmount_record(log, tic, &lsn, flags); /* * At this point, we're umounting anyway, so there's no point in * transitioning log state to IOERROR. Just continue... @@ -943,8 +857,7 @@ out_err: if (tic) { trace_xfs_log_umount_write(log, tic); - xlog_ungrant_log_space(log, tic); - xfs_log_ticket_put(tic); + xfs_log_ticket_ungrant(log, tic); } } @@ -987,8 +900,22 @@ xfs_log_unmount_write( if (XLOG_FORCED_SHUTDOWN(log)) return; + + /* + * If we think the summary counters are bad, avoid writing the unmount + * record to force log recovery at next mount, after which the summary + * counters will be recalculated. Refer to xlog_check_unmount_rec for + * more details. + */ + if (XFS_TEST_ERROR(xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS), mp, + XFS_ERRTAG_FORCE_SUMMARY_RECALC)) { + xfs_alert(mp, "%s: will fix summary counters at next mount", + __func__); + return; + } + xfs_log_unmount_verify_iclog(log); - xfs_log_write_unmount_record(mp); + xlog_unmount_write(log); } /* @@ -1515,20 +1442,17 @@ out: return ERR_PTR(error); } /* xlog_alloc_log */ - /* * Write out the commit record of a transaction associated with the given - * ticket. Return the lsn of the commit record. + * ticket to close off a running log write. Return the lsn of the commit record. */ -STATIC int +int xlog_commit_record( struct xlog *log, struct xlog_ticket *ticket, struct xlog_in_core **iclog, - xfs_lsn_t *commitlsnp) + xfs_lsn_t *lsn) { - struct xfs_mount *mp = log->l_mp; - int error; struct xfs_log_iovec reg = { .i_addr = NULL, .i_len = 0, @@ -1538,12 +1462,15 @@ xlog_commit_record( .lv_niovecs = 1, .lv_iovecp = ®, }; + int error; + + if (XLOG_FORCED_SHUTDOWN(log)) + return -EIO; - ASSERT_ALWAYS(iclog); - error = xlog_write(log, &vec, ticket, commitlsnp, iclog, - XLOG_COMMIT_TRANS); + error = xlog_write(log, &vec, ticket, lsn, iclog, XLOG_COMMIT_TRANS, + false); if (error) - xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR); + xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); return error; } @@ -1761,7 +1688,15 @@ xlog_write_iclog( iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart + bno; iclog->ic_bio.bi_end_io = xlog_bio_end_io; iclog->ic_bio.bi_private = iclog; - iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_FUA; + + /* + * We use REQ_SYNC | REQ_IDLE here to tell the block layer the are more + * IOs coming immediately after this one. This prevents the block layer + * writeback throttle from throttling log writes behind background + * metadata writeback and causing priority inversions. + */ + iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | + REQ_IDLE | REQ_FUA; if (need_flush) iclog->ic_bio.bi_opf |= REQ_PREFLUSH; @@ -1981,7 +1916,7 @@ xlog_dealloc_log( log->l_mp->m_log = NULL; destroy_workqueue(log->l_ioend_workqueue); kmem_free(log); -} /* xlog_dealloc_log */ +} /* * Update counters atomically now that memcpy is done. @@ -2118,23 +2053,21 @@ xlog_print_trans( } /* - * Calculate the potential space needed by the log vector. Each region gets - * its own xlog_op_header_t and may need to be double word aligned. + * Calculate the potential space needed by the log vector. We may need a start + * record, and each region gets its own struct xlog_op_header and may need to be + * double word aligned. */ static int xlog_write_calc_vec_length( struct xlog_ticket *ticket, - struct xfs_log_vec *log_vector) + struct xfs_log_vec *log_vector, + bool need_start_rec) { struct xfs_log_vec *lv; - int headers = 0; + int headers = need_start_rec ? 1 : 0; int len = 0; int i; - /* acct for start rec of xact */ - if (ticket->t_flags & XLOG_TIC_INITED) - headers++; - for (lv = log_vector; lv; lv = lv->lv_next) { /* we don't write ordered log vectors */ if (lv->lv_buf_len == XFS_LOG_VEC_ORDERED) @@ -2156,27 +2089,16 @@ xlog_write_calc_vec_length( return len; } -/* - * If first write for transaction, insert start record We can't be trying to - * commit if we are inited. We can't have any "partial_copy" if we are inited. - */ -static int +static void xlog_write_start_rec( struct xlog_op_header *ophdr, struct xlog_ticket *ticket) { - if (!(ticket->t_flags & XLOG_TIC_INITED)) - return 0; - ophdr->oh_tid = cpu_to_be32(ticket->t_tid); ophdr->oh_clientid = ticket->t_clientid; ophdr->oh_len = 0; ophdr->oh_flags = XLOG_START_TRANS; ophdr->oh_res2 = 0; - - ticket->t_flags &= ~XLOG_TIC_INITED; - - return sizeof(struct xlog_op_header); } static xlog_op_header_t * @@ -2365,13 +2287,14 @@ xlog_write( struct xlog_ticket *ticket, xfs_lsn_t *start_lsn, struct xlog_in_core **commit_iclog, - uint flags) + uint flags, + bool need_start_rec) { struct xlog_in_core *iclog = NULL; - struct xfs_log_iovec *vecp; - struct xfs_log_vec *lv; + struct xfs_log_vec *lv = log_vector; + struct xfs_log_iovec *vecp = lv->lv_iovecp; + int index = 0; int len; - int index; int partial_copy = 0; int partial_copy_len = 0; int contwr = 0; @@ -2379,25 +2302,13 @@ xlog_write( int data_cnt = 0; int error = 0; - *start_lsn = 0; - - len = xlog_write_calc_vec_length(ticket, log_vector); - /* - * Region headers and bytes are already accounted for. - * We only need to take into account start records and - * split regions in this function. + * If this is a commit or unmount transaction, we don't need a start + * record to be written. We do, however, have to account for the + * commit or unmount header that gets written. Hence we always have + * to account for an extra xlog_op_header here. */ - if (ticket->t_flags & XLOG_TIC_INITED) - ticket->t_curr_res -= sizeof(xlog_op_header_t); - - /* - * Commit record headers need to be accounted for. These - * come in as separate writes so are easy to detect. - */ - if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS)) - ticket->t_curr_res -= sizeof(xlog_op_header_t); - + ticket->t_curr_res -= sizeof(struct xlog_op_header); if (ticket->t_curr_res < 0) { xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, "ctx ticket reservation ran out. Need to up reservation"); @@ -2405,9 +2316,8 @@ xlog_write( xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); } - index = 0; - lv = log_vector; - vecp = lv->lv_iovecp; + len = xlog_write_calc_vec_length(ticket, log_vector, need_start_rec); + *start_lsn = 0; while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) { void *ptr; int log_offset; @@ -2431,7 +2341,6 @@ xlog_write( while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) { struct xfs_log_iovec *reg; struct xlog_op_header *ophdr; - int start_rec_copy; int copy_len; int copy_off; bool ordered = false; @@ -2447,11 +2356,15 @@ xlog_write( ASSERT(reg->i_len % sizeof(int32_t) == 0); ASSERT((unsigned long)ptr % sizeof(int32_t) == 0); - start_rec_copy = xlog_write_start_rec(ptr, ticket); - if (start_rec_copy) { - record_cnt++; + /* + * Before we start formatting log vectors, we need to + * write a start record. Only do this for the first + * iclog we write to. + */ + if (need_start_rec) { + xlog_write_start_rec(ptr, ticket); xlog_write_adv_cnt(&ptr, &len, &log_offset, - start_rec_copy); + sizeof(struct xlog_op_header)); } ophdr = xlog_write_setup_ophdr(log, ptr, ticket, flags); @@ -2483,8 +2396,13 @@ xlog_write( xlog_write_adv_cnt(&ptr, &len, &log_offset, copy_len); } - copy_len += start_rec_copy + sizeof(xlog_op_header_t); + copy_len += sizeof(struct xlog_op_header); record_cnt++; + if (need_start_rec) { + copy_len += sizeof(struct xlog_op_header); + record_cnt++; + need_start_rec = false; + } data_cnt += contwr ? copy_len : 0; error = xlog_write_copy_finish(log, iclog, flags, @@ -2541,14 +2459,6 @@ next_lv: return error; } - -/***************************************************************************** - * - * State Machine functions - * - ***************************************************************************** - */ - static void xlog_state_activate_iclog( struct xlog_in_core *iclog, @@ -2909,7 +2819,7 @@ xlog_state_done_syncing( */ wake_up_all(&iclog->ic_write_wait); spin_unlock(&log->l_icloglock); - xlog_state_do_callback(log); /* also cleans log */ + xlog_state_do_callback(log); } /* @@ -3029,21 +2939,21 @@ restart: *logoffsetp = log_offset; return 0; -} /* xlog_state_get_iclog_space */ - -/* The first cnt-1 times through here we don't need to - * move the grant write head because the permanent - * reservation has reserved cnt times the unit amount. - * Release part of current permanent unit reservation and - * reset current reservation to be one units worth. Also - * move grant reservation head forward. +} + +/* + * The first cnt-1 times a ticket goes through here we don't need to move the + * grant write head because the permanent reservation has reserved cnt times the + * unit amount. Release part of current permanent unit reservation and reset + * current reservation to be one units worth. Also move grant reservation head + * forward. */ -STATIC void -xlog_regrant_reserve_log_space( +void +xfs_log_ticket_regrant( struct xlog *log, struct xlog_ticket *ticket) { - trace_xfs_log_regrant_reserve_enter(log, ticket); + trace_xfs_log_ticket_regrant(log, ticket); if (ticket->t_cnt > 0) ticket->t_cnt--; @@ -3055,21 +2965,20 @@ xlog_regrant_reserve_log_space( ticket->t_curr_res = ticket->t_unit_res; xlog_tic_reset_res(ticket); - trace_xfs_log_regrant_reserve_sub(log, ticket); + trace_xfs_log_ticket_regrant_sub(log, ticket); /* just return if we still have some of the pre-reserved space */ - if (ticket->t_cnt > 0) - return; + if (!ticket->t_cnt) { + xlog_grant_add_space(log, &log->l_reserve_head.grant, + ticket->t_unit_res); + trace_xfs_log_ticket_regrant_exit(log, ticket); - xlog_grant_add_space(log, &log->l_reserve_head.grant, - ticket->t_unit_res); - - trace_xfs_log_regrant_reserve_exit(log, ticket); - - ticket->t_curr_res = ticket->t_unit_res; - xlog_tic_reset_res(ticket); -} /* xlog_regrant_reserve_log_space */ + ticket->t_curr_res = ticket->t_unit_res; + xlog_tic_reset_res(ticket); + } + xfs_log_ticket_put(ticket); +} /* * Give back the space left from a reservation. @@ -3085,18 +2994,19 @@ xlog_regrant_reserve_log_space( * space, the count will stay at zero and the only space remaining will be * in the current reservation field. */ -STATIC void -xlog_ungrant_log_space( +void +xfs_log_ticket_ungrant( struct xlog *log, struct xlog_ticket *ticket) { - int bytes; + int bytes; + + trace_xfs_log_ticket_ungrant(log, ticket); if (ticket->t_cnt > 0) ticket->t_cnt--; - trace_xfs_log_ungrant_enter(log, ticket); - trace_xfs_log_ungrant_sub(log, ticket); + trace_xfs_log_ticket_ungrant_sub(log, ticket); /* * If this is a permanent reservation ticket, we may be able to free @@ -3111,18 +3021,15 @@ xlog_ungrant_log_space( xlog_grant_sub_space(log, &log->l_reserve_head.grant, bytes); xlog_grant_sub_space(log, &log->l_write_head.grant, bytes); - trace_xfs_log_ungrant_exit(log, ticket); + trace_xfs_log_ticket_ungrant_exit(log, ticket); xfs_log_space_wake(log->l_mp); + xfs_log_ticket_put(ticket); } /* - * Mark the current iclog in the ring as WANT_SYNC and move the current iclog - * pointer to the next iclog in the ring. - * - * When called from xlog_state_get_iclog_space(), the exact size of the iclog - * has not yet been determined, all we know is that we have run out of space in - * the current iclog. + * This routine will mark the current iclog in the ring as WANT_SYNC and move + * the current iclog pointer to the next iclog in the ring. */ STATIC void xlog_state_switch_iclogs( @@ -3167,7 +3074,7 @@ xlog_state_switch_iclogs( } ASSERT(iclog == log->l_iclog); log->l_iclog = iclog->ic_next; -} /* xlog_state_switch_iclogs */ +} /* * Write out all data in the in-core log as of this exact moment in time. @@ -3374,13 +3281,6 @@ xfs_log_force_lsn( return ret; } -/***************************************************************************** - * - * TICKET functions - * - ***************************************************************************** - */ - /* * Free a used ticket when its refcount falls to zero. */ @@ -3529,7 +3429,6 @@ xlog_ticket_alloc( tic->t_ocnt = cnt; tic->t_tid = prandom_u32(); tic->t_clientid = client; - tic->t_flags = XLOG_TIC_INITED; if (permanent) tic->t_flags |= XLOG_TIC_PERM_RESERV; @@ -3538,13 +3437,6 @@ xlog_ticket_alloc( return tic; } - -/****************************************************************************** - * - * Log debug routines - * - ****************************************************************************** - */ #if defined(DEBUG) /* * Make sure that the destination ptr is within the valid data region of @@ -3630,7 +3522,7 @@ xlog_verify_tail_lsn( if (blocks < BTOBB(iclog->ic_offset) + 1) xfs_emerg(log->l_mp, "%s: ran out of log space", __func__); } -} /* xlog_verify_tail_lsn */ +} /* * Perform a number of checks on the iclog before writing to disk. @@ -3733,7 +3625,7 @@ xlog_verify_iclog( } ptr += sizeof(xlog_op_header_t) + op_len; } -} /* xlog_verify_iclog */ +} #endif /* diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index cc77cc36560a..1412d6993f1e 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -105,10 +105,6 @@ struct xfs_log_item; struct xfs_item_ops; struct xfs_trans; -xfs_lsn_t xfs_log_done(struct xfs_mount *mp, - struct xlog_ticket *ticket, - struct xlog_in_core **iclog, - bool regrant); int xfs_log_force(struct xfs_mount *mp, uint flags); int xfs_log_force_lsn(struct xfs_mount *mp, xfs_lsn_t lsn, uint flags, int *log_forced); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 64cc0bf2ab3b..b43f0e8f43f2 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -669,6 +669,11 @@ xlog_cil_push_work( ASSERT(push_seq <= ctx->sequence); /* + * Wake up any background push waiters now this context is being pushed. + */ + wake_up_all(&ctx->push_wait); + + /* * Check if we've anything to push. If there is nothing, then we don't * move on to a new sequence number and so we have to be able to push * this sequence again later. @@ -744,6 +749,7 @@ xlog_cil_push_work( */ INIT_LIST_HEAD(&new_ctx->committing); INIT_LIST_HEAD(&new_ctx->busy_extents); + init_waitqueue_head(&new_ctx->push_wait); new_ctx->sequence = ctx->sequence + 1; new_ctx->cil = cil; cil->xc_ctx = new_ctx; @@ -801,7 +807,7 @@ xlog_cil_push_work( lvhdr.lv_iovecp = &lhdr; lvhdr.lv_next = ctx->lv_chain; - error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0); + error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0, true); if (error) goto out_abort_free_ticket; @@ -839,10 +845,11 @@ restart: } spin_unlock(&cil->xc_push_lock); - /* xfs_log_done always frees the ticket on error. */ - commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, false); - if (commit_lsn == -1) - goto out_abort; + error = xlog_commit_record(log, tic, &commit_iclog, &commit_lsn); + if (error) + goto out_abort_free_ticket; + + xfs_log_ticket_ungrant(log, tic); spin_lock(&commit_iclog->ic_callback_lock); if (commit_iclog->ic_state == XLOG_STATE_IOERROR) { @@ -875,7 +882,7 @@ out_skip: return; out_abort_free_ticket: - xfs_log_ticket_put(tic); + xfs_log_ticket_ungrant(log, tic); out_abort: ASSERT(XLOG_FORCED_SHUTDOWN(log)); xlog_cil_committed(ctx); @@ -890,7 +897,7 @@ out_abort: */ static void xlog_cil_push_background( - struct xlog *log) + struct xlog *log) __releases(cil->xc_ctx_lock) { struct xfs_cil *cil = log->l_cilp; @@ -904,14 +911,36 @@ xlog_cil_push_background( * don't do a background push if we haven't used up all the * space available yet. */ - if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) + if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) { + up_read(&cil->xc_ctx_lock); return; + } spin_lock(&cil->xc_push_lock); if (cil->xc_push_seq < cil->xc_current_sequence) { cil->xc_push_seq = cil->xc_current_sequence; queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work); } + + /* + * Drop the context lock now, we can't hold that if we need to sleep + * because we are over the blocking threshold. The push_lock is still + * held, so blocking threshold sleep/wakeup is still correctly + * serialised here. + */ + up_read(&cil->xc_ctx_lock); + + /* + * If we are well over the space limit, throttle the work that is being + * done until the push work on this context has begun. + */ + if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) { + trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket); + ASSERT(cil->xc_ctx->space_used < log->l_logsize); + xlog_wait(&cil->xc_ctx->push_wait, &cil->xc_push_lock); + return; + } + spin_unlock(&cil->xc_push_lock); } @@ -1007,7 +1036,10 @@ xfs_log_commit_cil( if (commit_lsn) *commit_lsn = xc_commit_lsn; - xfs_log_done(mp, tp->t_ticket, NULL, regrant); + if (regrant && !XLOG_FORCED_SHUTDOWN(log)) + xfs_log_ticket_regrant(log, tp->t_ticket); + else + xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; xfs_trans_unreserve_and_mod_sb(tp); @@ -1028,9 +1060,9 @@ xfs_log_commit_cil( if (lip->li_ops->iop_committing) lip->li_ops->iop_committing(lip, xc_commit_lsn); } - xlog_cil_push_background(log); - up_read(&cil->xc_ctx_lock); + /* xlog_cil_push_background() releases cil->xc_ctx_lock */ + xlog_cil_push_background(log); } /* @@ -1189,6 +1221,7 @@ xlog_cil_init( INIT_LIST_HEAD(&ctx->committing); INIT_LIST_HEAD(&ctx->busy_extents); + init_waitqueue_head(&ctx->push_wait); ctx->sequence = 1; ctx->cil = cil; cil->xc_ctx = ctx; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 2b0aec37e73e..ec22c7a3867f 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -51,13 +51,11 @@ enum xlog_iclog_state { }; /* - * Flags to log ticket + * Log ticket flags */ -#define XLOG_TIC_INITED 0x1 /* has been initialized */ -#define XLOG_TIC_PERM_RESERV 0x2 /* permanent reservation */ +#define XLOG_TIC_PERM_RESERV 0x1 /* permanent reservation */ #define XLOG_TIC_FLAGS \ - { XLOG_TIC_INITED, "XLOG_TIC_INITED" }, \ { XLOG_TIC_PERM_RESERV, "XLOG_TIC_PERM_RESERV" } /* @@ -242,6 +240,7 @@ struct xfs_cil_ctx { struct xfs_log_vec *lv_chain; /* logvecs being pushed */ struct list_head iclog_entry; struct list_head committing; /* ctx committing list */ + wait_queue_head_t push_wait; /* background push throttle */ struct work_struct discard_endio_work; }; @@ -318,13 +317,53 @@ struct xfs_cil { * tries to keep 25% of the log free, so we need to keep below that limit or we * risk running out of free log space to start any new transactions. * - * In order to keep background CIL push efficient, we will set a lower - * threshold at which background pushing is attempted without blocking current - * transaction commits. A separate, higher bound defines when CIL pushes are - * enforced to ensure we stay within our maximum checkpoint size bounds. - * threshold, yet give us plenty of space for aggregation on large logs. + * In order to keep background CIL push efficient, we only need to ensure the + * CIL is large enough to maintain sufficient in-memory relogging to avoid + * repeated physical writes of frequently modified metadata. If we allow the CIL + * to grow to a substantial fraction of the log, then we may be pinning hundreds + * of megabytes of metadata in memory until the CIL flushes. This can cause + * issues when we are running low on memory - pinned memory cannot be reclaimed, + * and the CIL consumes a lot of memory. Hence we need to set an upper physical + * size limit for the CIL that limits the maximum amount of memory pinned by the + * CIL but does not limit performance by reducing relogging efficiency + * significantly. + * + * As such, the CIL push threshold ends up being the smaller of two thresholds: + * - a threshold large enough that it allows CIL to be pushed and progress to be + * made without excessive blocking of incoming transaction commits. This is + * defined to be 12.5% of the log space - half the 25% push threshold of the + * AIL. + * - small enough that it doesn't pin excessive amounts of memory but maintains + * close to peak relogging efficiency. This is defined to be 16x the iclog + * buffer window (32MB) as measurements have shown this to be roughly the + * point of diminishing performance increases under highly concurrent + * modification workloads. + * + * To prevent the CIL from overflowing upper commit size bounds, we introduce a + * new threshold at which we block committing transactions until the background + * CIL commit commences and switches to a new context. While this is not a hard + * limit, it forces the process committing a transaction to the CIL to block and + * yeild the CPU, giving the CIL push work a chance to be scheduled and start + * work. This prevents a process running lots of transactions from overfilling + * the CIL because it is not yielding the CPU. We set the blocking limit at + * twice the background push space threshold so we keep in line with the AIL + * push thresholds. + * + * Note: this is not a -hard- limit as blocking is applied after the transaction + * is inserted into the CIL and the push has been triggered. It is largely a + * throttling mechanism that allows the CIL push to be scheduled and run. A hard + * limit will be difficult to implement without introducing global serialisation + * in the CIL commit fast path, and it's not at all clear that we actually need + * such hard limits given the ~7 years we've run without a hard limit before + * finding the first situation where a checkpoint size overflow actually + * occurred. Hence the simple throttle, and an ASSERT check to tell us that + * we've overrun the max size. */ -#define XLOG_CIL_SPACE_LIMIT(log) (log->l_logsize >> 3) +#define XLOG_CIL_SPACE_LIMIT(log) \ + min_t(int, (log)->l_logsize >> 3, BBTOB(XLOG_TOTAL_REC_SHIFT(log)) << 4) + +#define XLOG_CIL_BLOCKING_SPACE_LIMIT(log) \ + (XLOG_CIL_SPACE_LIMIT(log) * 2) /* * ticket grant locks, queues and accounting have their own cachlines @@ -439,14 +478,14 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes) void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket); void xlog_print_trans(struct xfs_trans *); -int -xlog_write( - struct xlog *log, - struct xfs_log_vec *log_vector, - struct xlog_ticket *tic, - xfs_lsn_t *start_lsn, - struct xlog_in_core **commit_iclog, - uint flags); +int xlog_write(struct xlog *log, struct xfs_log_vec *log_vector, + struct xlog_ticket *tic, xfs_lsn_t *start_lsn, + struct xlog_in_core **commit_iclog, uint flags, + bool need_start_rec); +int xlog_commit_record(struct xlog *log, struct xlog_ticket *ticket, + struct xlog_in_core **iclog, xfs_lsn_t *lsn); +void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket); +void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket); /* * When we crack an atomic LSN, we sample it first so that the value will not diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 88ab09ed29e7..50c43422fa17 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -167,6 +167,7 @@ typedef struct xfs_mount { struct xfs_kobj m_error_meta_kobj; struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX]; struct xstats m_stats; /* per-fs stats */ + struct ratelimit_state m_flush_inodes_ratelimit; struct workqueue_struct *m_buf_workqueue; struct workqueue_struct *m_unwritten_workqueue; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index cabdb755adae..c225691fad15 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -121,12 +121,11 @@ xfs_qm_dqpurge( { struct xfs_mount *mp = dqp->q_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; + int error = -EAGAIN; xfs_dqlock(dqp); - if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) { - xfs_dqunlock(dqp); - return -EAGAIN; - } + if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) + goto out_unlock; dqp->dq_flags |= XFS_DQ_FREEING; @@ -139,7 +138,6 @@ xfs_qm_dqpurge( */ if (XFS_DQ_IS_DIRTY(dqp)) { struct xfs_buf *bp = NULL; - int error; /* * We don't care about getting disk errors here. We need @@ -149,6 +147,8 @@ xfs_qm_dqpurge( if (!error) { error = xfs_bwrite(bp); xfs_buf_relse(bp); + } else if (error == -EAGAIN) { + goto out_unlock; } xfs_dqflock(dqp); } @@ -174,6 +174,10 @@ xfs_qm_dqpurge( xfs_qm_dqdestroy(dqp); return 0; + +out_unlock: + xfs_dqunlock(dqp); + return error; } /* diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 2094386af8ac..abf06bf9c3f3 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -528,6 +528,9 @@ xfs_flush_inodes( { struct super_block *sb = mp->m_super; + if (!__ratelimit(&mp->m_flush_inodes_ratelimit)) + return; + if (down_read_trylock(&sb->s_umount)) { sync_inodes_sb(sb); up_read(&sb->s_umount); @@ -1366,6 +1369,17 @@ xfs_fc_fill_super( if (error) goto out_free_names; + /* + * Cap the number of invocations of xfs_flush_inodes to 16 for every + * quarter of a second. The magic numbers here were determined by + * observation neither to cause stalls in writeback when there are a + * lot of IO threads and the fs is near ENOSPC, nor cause any fstest + * regressions. YMMV. + */ + ratelimit_state_init(&mp->m_flush_inodes_ratelimit, HZ / 4, 16); + ratelimit_set_flags(&mp->m_flush_inodes_ratelimit, + RATELIMIT_MSG_ON_RELEASE); + error = xfs_init_mount_workqueues(mp); if (error) goto out_close_devices; @@ -1861,7 +1875,8 @@ xfs_init_zones(void) xfs_ili_zone = kmem_cache_create("xfs_ili", sizeof(struct xfs_inode_log_item), 0, - SLAB_MEM_SPREAD, NULL); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, + NULL); if (!xfs_ili_zone) goto out_destroy_inode_zone; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index fa0fa3c70f1a..13fb4b919648 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -176,7 +176,6 @@ xfs_symlink( return -ENAMETOOLONG; ASSERT(pathlen > 0); - udqp = gdqp = NULL; prid = xfs_get_initial_prid(dp); /* diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index efc7751550d9..a4323a63438d 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1001,8 +1001,6 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class, DEFINE_EVENT(xfs_loggrant_class, name, \ TP_PROTO(struct xlog *log, struct xlog_ticket *tic), \ TP_ARGS(log, tic)) -DEFINE_LOGGRANT_EVENT(xfs_log_done_nonperm); -DEFINE_LOGGRANT_EVENT(xfs_log_done_perm); DEFINE_LOGGRANT_EVENT(xfs_log_umount_write); DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep); DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake); @@ -1011,12 +1009,13 @@ DEFINE_LOGGRANT_EVENT(xfs_log_reserve); DEFINE_LOGGRANT_EVENT(xfs_log_reserve_exit); DEFINE_LOGGRANT_EVENT(xfs_log_regrant); DEFINE_LOGGRANT_EVENT(xfs_log_regrant_exit); -DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_enter); -DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_exit); -DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_sub); -DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_enter); -DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_exit); -DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_sub); +DEFINE_LOGGRANT_EVENT(xfs_log_ticket_regrant); +DEFINE_LOGGRANT_EVENT(xfs_log_ticket_regrant_exit); +DEFINE_LOGGRANT_EVENT(xfs_log_ticket_regrant_sub); +DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant); +DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant_sub); +DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant_exit); +DEFINE_LOGGRANT_EVENT(xfs_log_cil_wait); DECLARE_EVENT_CLASS(xfs_log_item_class, TP_PROTO(struct xfs_log_item *lip), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 1adc6bc53a56..28b983ff8b11 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -9,6 +9,7 @@ #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" +#include "xfs_log_priv.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_extent_busy.h" @@ -150,8 +151,9 @@ xfs_trans_reserve( uint blocks, uint rtextents) { - int error = 0; - bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; + struct xfs_mount *mp = tp->t_mountp; + int error = 0; + bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; /* Mark this thread as being in a transaction */ current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); @@ -162,7 +164,7 @@ xfs_trans_reserve( * fail if the count would go below zero. */ if (blocks > 0) { - error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd); + error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd); if (error != 0) { current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); return -ENOSPC; @@ -191,9 +193,9 @@ xfs_trans_reserve( if (tp->t_ticket != NULL) { ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES); - error = xfs_log_regrant(tp->t_mountp, tp->t_ticket); + error = xfs_log_regrant(mp, tp->t_ticket); } else { - error = xfs_log_reserve(tp->t_mountp, + error = xfs_log_reserve(mp, resp->tr_logres, resp->tr_logcount, &tp->t_ticket, XFS_TRANSACTION, @@ -213,7 +215,7 @@ xfs_trans_reserve( * fail if the count would go below zero. */ if (rtextents > 0) { - error = xfs_mod_frextents(tp->t_mountp, -((int64_t)rtextents)); + error = xfs_mod_frextents(mp, -((int64_t)rtextents)); if (error) { error = -ENOSPC; goto undo_log; @@ -229,7 +231,7 @@ xfs_trans_reserve( */ undo_log: if (resp->tr_logres > 0) { - xfs_log_done(tp->t_mountp, tp->t_ticket, NULL, false); + xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); tp->t_ticket = NULL; tp->t_log_res = 0; tp->t_flags &= ~XFS_TRANS_PERM_LOG_RES; @@ -237,7 +239,7 @@ undo_log: undo_blocks: if (blocks > 0) { - xfs_mod_fdblocks(tp->t_mountp, (int64_t)blocks, rsvd); + xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd); tp->t_blk_res = 0; } @@ -1004,9 +1006,10 @@ out_unreserve: */ xfs_trans_unreserve_and_mod_dquots(tp); if (tp->t_ticket) { - commit_lsn = xfs_log_done(mp, tp->t_ticket, NULL, regrant); - if (commit_lsn == -1 && !error) - error = -EIO; + if (regrant && !XLOG_FORCED_SHUTDOWN(mp->m_log)) + xfs_log_ticket_regrant(mp->m_log, tp->t_ticket); + else + xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); tp->t_ticket = NULL; } current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); @@ -1065,7 +1068,7 @@ xfs_trans_cancel( xfs_trans_unreserve_and_mod_dquots(tp); if (tp->t_ticket) { - xfs_log_done(mp, tp->t_ticket, NULL, false); + xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); tp->t_ticket = NULL; } diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 2ef0dfbfb303..564253550b75 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -109,17 +109,25 @@ xfs_ail_next( * We need the AIL lock in order to get a coherent read of the lsn of the last * item in the AIL. */ +static xfs_lsn_t +__xfs_ail_min_lsn( + struct xfs_ail *ailp) +{ + struct xfs_log_item *lip = xfs_ail_min(ailp); + + if (lip) + return lip->li_lsn; + return 0; +} + xfs_lsn_t xfs_ail_min_lsn( struct xfs_ail *ailp) { - xfs_lsn_t lsn = 0; - struct xfs_log_item *lip; + xfs_lsn_t lsn; spin_lock(&ailp->ail_lock); - lip = xfs_ail_min(ailp); - if (lip) - lsn = lip->li_lsn; + lsn = __xfs_ail_min_lsn(ailp); spin_unlock(&ailp->ail_lock); return lsn; @@ -681,6 +689,28 @@ xfs_ail_push_all_sync( finish_wait(&ailp->ail_empty, &wait); } +void +xfs_ail_update_finish( + struct xfs_ail *ailp, + xfs_lsn_t old_lsn) __releases(ailp->ail_lock) +{ + struct xfs_mount *mp = ailp->ail_mount; + + /* if the tail lsn hasn't changed, don't do updates or wakeups. */ + if (!old_lsn || old_lsn == __xfs_ail_min_lsn(ailp)) { + spin_unlock(&ailp->ail_lock); + return; + } + + if (!XFS_FORCED_SHUTDOWN(mp)) + xlog_assign_tail_lsn_locked(mp); + + if (list_empty(&ailp->ail_head)) + wake_up_all(&ailp->ail_empty); + spin_unlock(&ailp->ail_lock); + xfs_log_space_wake(mp); +} + /* * xfs_trans_ail_update - bulk AIL insertion operation. * @@ -712,7 +742,7 @@ xfs_trans_ail_update_bulk( xfs_lsn_t lsn) __releases(ailp->ail_lock) { struct xfs_log_item *mlip; - int mlip_changed = 0; + xfs_lsn_t tail_lsn = 0; int i; LIST_HEAD(tmp); @@ -727,9 +757,10 @@ xfs_trans_ail_update_bulk( continue; trace_xfs_ail_move(lip, lip->li_lsn, lsn); + if (mlip == lip && !tail_lsn) + tail_lsn = lip->li_lsn; + xfs_ail_delete(ailp, lip); - if (mlip == lip) - mlip_changed = 1; } else { trace_xfs_ail_insert(lip, 0, lsn); } @@ -740,23 +771,23 @@ xfs_trans_ail_update_bulk( if (!list_empty(&tmp)) xfs_ail_splice(ailp, cur, &tmp, lsn); - if (mlip_changed) { - if (!XFS_FORCED_SHUTDOWN(ailp->ail_mount)) - xlog_assign_tail_lsn_locked(ailp->ail_mount); - spin_unlock(&ailp->ail_lock); - - xfs_log_space_wake(ailp->ail_mount); - } else { - spin_unlock(&ailp->ail_lock); - } + xfs_ail_update_finish(ailp, tail_lsn); } -bool +/* + * Delete one log item from the AIL. + * + * If this item was at the tail of the AIL, return the LSN of the log item so + * that we can use it to check if the LSN of the tail of the log has moved + * when finishing up the AIL delete process in xfs_ail_update_finish(). + */ +xfs_lsn_t xfs_ail_delete_one( struct xfs_ail *ailp, struct xfs_log_item *lip) { struct xfs_log_item *mlip = xfs_ail_min(ailp); + xfs_lsn_t lsn = lip->li_lsn; trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); xfs_ail_delete(ailp, lip); @@ -764,7 +795,9 @@ xfs_ail_delete_one( clear_bit(XFS_LI_IN_AIL, &lip->li_flags); lip->li_lsn = 0; - return mlip == lip; + if (mlip == lip) + return lsn; + return 0; } /** @@ -792,10 +825,10 @@ void xfs_trans_ail_delete( struct xfs_ail *ailp, struct xfs_log_item *lip, - int shutdown_type) __releases(ailp->ail_lock) + int shutdown_type) { struct xfs_mount *mp = ailp->ail_mount; - bool mlip_changed; + xfs_lsn_t tail_lsn; if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) { spin_unlock(&ailp->ail_lock); @@ -808,17 +841,8 @@ xfs_trans_ail_delete( return; } - mlip_changed = xfs_ail_delete_one(ailp, lip); - if (mlip_changed) { - if (!XFS_FORCED_SHUTDOWN(mp)) - xlog_assign_tail_lsn_locked(mp); - if (list_empty(&ailp->ail_head)) - wake_up_all(&ailp->ail_empty); - } - - spin_unlock(&ailp->ail_lock); - if (mlip_changed) - xfs_log_space_wake(ailp->ail_mount); + tail_lsn = xfs_ail_delete_one(ailp, lip); + xfs_ail_update_finish(ailp, tail_lsn); } int diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 2e073c1c4614..35655eac01a6 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -91,9 +91,11 @@ xfs_trans_ail_update( xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn); } -bool xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip); +xfs_lsn_t xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip); +void xfs_ail_update_finish(struct xfs_ail *ailp, xfs_lsn_t old_lsn) + __releases(ailp->ail_lock); void xfs_trans_ail_delete(struct xfs_ail *ailp, struct xfs_log_item *lip, - int shutdown_type) __releases(ailp->ail_lock); + int shutdown_type); static inline void xfs_trans_ail_remove( |