From patchwork Tue Apr 4 07:50:39 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Weinberger X-Patchwork-Id: 13199232 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id C5F21C761A6 for ; Tue, 4 Apr 2023 07:51:06 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229488AbjDDHvF (ORCPT ); Tue, 4 Apr 2023 03:51:05 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53966 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230193AbjDDHvE (ORCPT ); Tue, 4 Apr 2023 03:51:04 -0400 Received: from lithops.sigma-star.at (lithops.sigma-star.at [195.201.40.130]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EE3C510FC for ; Tue, 4 Apr 2023 00:50:58 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by lithops.sigma-star.at (Postfix) with ESMTP id A683F64548A5; Tue, 4 Apr 2023 09:50:56 +0200 (CEST) Received: from lithops.sigma-star.at ([127.0.0.1]) by localhost (lithops.sigma-star.at [127.0.0.1]) (amavisd-new, port 10032) with ESMTP id UGV3SvohDLna; Tue, 4 Apr 2023 09:50:55 +0200 (CEST) Received: from localhost (localhost [127.0.0.1]) by lithops.sigma-star.at (Postfix) with ESMTP id CB3E864548A1; Tue, 4 Apr 2023 09:50:55 +0200 (CEST) Received: from lithops.sigma-star.at ([127.0.0.1]) by localhost (lithops.sigma-star.at [127.0.0.1]) (amavisd-new, port 10026) with ESMTP id HTYssVk60pAP; Tue, 4 Apr 2023 09:50:55 +0200 (CEST) Received: from blindfold.corp.sigma-star.at (213-47-184-186.cable.dynamic.surfer.at [213.47.184.186]) by lithops.sigma-star.at (Postfix) with ESMTPSA id 668B16418F2B; Tue, 4 Apr 2023 09:50:55 +0200 (CEST) From: Richard Weinberger To: linux-nfs@vger.kernel.org Cc: david@sigma-star.at, david.oberhollenzer@sigma-star.at, luis.turcitu@appsbroker.com, david.young@appsbroker.com, trond.myklebust@hammerspace.com, anna.schumaker@netapp.com, steved@redhat.com, chris.chilvers@appsbroker.com, Richard Weinberger Subject: [PATCH 2/2] Implement fsidd Date: Tue, 4 Apr 2023 09:50:39 +0200 Message-Id: <20230404075039.10802-3-richard@nod.at> X-Mailer: git-send-email 2.26.2 In-Reply-To: <20230404075039.10802-1-richard@nod.at> References: <20230404075039.10802-1-richard@nod.at> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-nfs@vger.kernel.org The file system id service is a small daemon which serves and creates fsids by a given path. Currently it supports only on backend, a sqlite database. Every nfs related service, such as mountd or exportfs can query it using a local domain socket. Signed-off-by: Richard Weinberger --- support/reexport/Makefile.am | 12 ++ support/reexport/backend_sqlite.c | 267 ++++++++++++++++++++++++++++++ support/reexport/fsidd.c | 198 ++++++++++++++++++++++ systemd/fsidd.service | 9 + 4 files changed, 486 insertions(+) create mode 100644 support/reexport/backend_sqlite.c create mode 100644 support/reexport/fsidd.c create mode 100644 systemd/fsidd.service diff --git a/support/reexport/Makefile.am b/support/reexport/Makefile.am index 9d544a8f..fbd66a20 100644 --- a/support/reexport/Makefile.am +++ b/support/reexport/Makefile.am @@ -3,4 +3,16 @@ noinst_LIBRARIES = libreexport.a libreexport_a_SOURCES = reexport.c +sbin_PROGRAMS = fsidd + +fsidd_SOURCES = fsidd.c backend_sqlite.c + +fsidd_LDADD = ../../support/misc/libmisc.a \ + ../../support/nfs/libnfs.la \ + $(LIBPTHREAD) $(LIBEVENT) $(LIBSQLITE) \ + $(OPTLIBS) + +fsidd_CPPFLAGS = $(AM_CPPFLAGS) $(CPPFLAGS) \ + -I$(top_builddir)/support/include + MAINTAINERCLEANFILES = Makefile.in diff --git a/support/reexport/backend_sqlite.c b/support/reexport/backend_sqlite.c new file mode 100644 index 00000000..132f30c4 --- /dev/null +++ b/support/reexport/backend_sqlite.c @@ -0,0 +1,267 @@ +#ifdef HAVE_CONFIG_H +#include +#endif + +#include +#include +#include +#include +#include +#include +#include + +#include "conffile.h" +#include "reexport_backend.h" +#include "xlog.h" + +#define REEXPDB_DBFILE NFS_STATEDIR "/reexpdb.sqlite3" +#define REEXPDB_DBFILE_WAIT_USEC (5000) + +static sqlite3 *db; +static int init_done; + +static int prng_init(void) +{ + int seed; + + if (getrandom(&seed, sizeof(seed), 0) != sizeof(seed)) { + xlog(L_ERROR, "Unable to obtain seed for PRNG via getrandom()"); + return -1; + } + + srand(seed); + return 0; +} + +static void wait_for_dbaccess(void) +{ + usleep(REEXPDB_DBFILE_WAIT_USEC + (rand() % REEXPDB_DBFILE_WAIT_USEC)); +} + +static bool sqlite_plug_init(void) +{ + char *sqlerr; + int ret; + + if (init_done) + return true; + + if (prng_init() != 0) + return false; + + ret = sqlite3_open_v2(conf_get_str_with_def("reexport", "sqlitedb", REEXPDB_DBFILE), + &db, SQLITE_OPEN_READWRITE | SQLITE_OPEN_CREATE | SQLITE_OPEN_FULLMUTEX, + NULL); + if (ret != SQLITE_OK) { + xlog(L_ERROR, "Unable to open reexport database: %s", sqlite3_errstr(ret)); + return false; + } + +again: + ret = sqlite3_exec(db, "CREATE TABLE IF NOT EXISTS fsidnums (num INTEGER PRIMARY KEY CHECK (num > 0 AND num < 4294967296), path TEXT UNIQUE); CREATE INDEX IF NOT EXISTS idx_ids_path ON fsidnums (path);", NULL, NULL, &sqlerr); + switch (ret) { + case SQLITE_OK: + init_done = 1; + ret = 0; + break; + case SQLITE_BUSY: + case SQLITE_LOCKED: + wait_for_dbaccess(); + goto again; + default: + xlog(L_ERROR, "Unable to init reexport database: %s", sqlite3_errstr(ret)); + sqlite3_free(sqlerr); + sqlite3_close_v2(db); + ret = -1; + } + + return ret == 0 ? true : false; +} + +static void sqlite_plug_destroy(void) +{ + if (!init_done) + return; + + sqlite3_close_v2(db); +} + +static bool get_fsidnum_by_path(char *path, uint32_t *fsidnum, bool *found) +{ + static const char fsidnum_by_path_sql[] = "SELECT num FROM fsidnums WHERE path = ?1;"; + sqlite3_stmt *stmt = NULL; + bool success = false; + int ret; + + *found = false; + + ret = sqlite3_prepare_v2(db, fsidnum_by_path_sql, sizeof(fsidnum_by_path_sql), &stmt, NULL); + if (ret != SQLITE_OK) { + xlog(L_WARNING, "Unable to prepare SQL query '%s': %s", fsidnum_by_path_sql, sqlite3_errstr(ret)); + goto out; + } + + ret = sqlite3_bind_text(stmt, 1, path, -1, NULL); + if (ret != SQLITE_OK) { + xlog(L_WARNING, "Unable to bind SQL query '%s': %s", fsidnum_by_path_sql, sqlite3_errstr(ret)); + goto out; + } + +again: + ret = sqlite3_step(stmt); + switch (ret) { + case SQLITE_ROW: + *fsidnum = sqlite3_column_int(stmt, 0); + success = true; + *found = true; + break; + case SQLITE_DONE: + /* No hit */ + success = true; + *found = false; + break; + case SQLITE_BUSY: + case SQLITE_LOCKED: + wait_for_dbaccess(); + goto again; + default: + xlog(L_WARNING, "Error while looking up '%s' in database: %s", path, sqlite3_errstr(ret)); + } + +out: + sqlite3_finalize(stmt); + return success; +} + +static bool sqlite_plug_path_by_fsidnum(uint32_t fsidnum, char **path, bool *found) +{ + static const char path_by_fsidnum_sql[] = "SELECT path FROM fsidnums WHERE num = ?1;"; + sqlite3_stmt *stmt = NULL; + bool success = false; + int ret; + + *found = false; + + ret = sqlite3_prepare_v2(db, path_by_fsidnum_sql, sizeof(path_by_fsidnum_sql), &stmt, NULL); + if (ret != SQLITE_OK) { + xlog(L_WARNING, "Unable to prepare SQL query '%s': %s", path_by_fsidnum_sql, sqlite3_errstr(ret)); + goto out; + } + + ret = sqlite3_bind_int(stmt, 1, fsidnum); + if (ret != SQLITE_OK) { + xlog(L_WARNING, "Unable to bind SQL query '%s': %s", path_by_fsidnum_sql, sqlite3_errstr(ret)); + goto out; + } + +again: + ret = sqlite3_step(stmt); + switch (ret) { + case SQLITE_ROW: + *path = strdup((char *)sqlite3_column_text(stmt, 0)); + if (*path) { + *found = true; + success = true; + } else { + xlog(L_WARNING, "Out of memory"); + } + break; + case SQLITE_DONE: + /* No hit */ + *found = false; + success = true; + break; + case SQLITE_BUSY: + case SQLITE_LOCKED: + wait_for_dbaccess(); + goto again; + default: + xlog(L_WARNING, "Error while looking up '%i' in database: %s", fsidnum, sqlite3_errstr(ret)); + } + +out: + sqlite3_finalize(stmt); + return success; +} + +static bool new_fsidnum_by_path(char *path, uint32_t *fsidnum) +{ + /* + * This query is a little tricky. We use SQL to find and claim the smallest free fsid number. + * To find a free fsid the fsidnums is left joined to itself but with an offset of 1. + * Everything after the UNION statement is to handle the corner case where fsidnums + * is empty. In this case we want 1 as first fsid number. + */ + static const char new_fsidnum_by_path_sql[] = "INSERT INTO fsidnums VALUES ((SELECT ids1.num + 1 FROM fsidnums AS ids1 LEFT JOIN fsidnums AS ids2 ON ids2.num = ids1.num + 1 WHERE ids2.num IS NULL UNION SELECT 1 WHERE NOT EXISTS (SELECT NULL FROM fsidnums WHERE num = 1) LIMIT 1), ?1) RETURNING num;"; + + sqlite3_stmt *stmt = NULL; + int ret, check = 0; + bool success = false; + + ret = sqlite3_prepare_v2(db, new_fsidnum_by_path_sql, sizeof(new_fsidnum_by_path_sql), &stmt, NULL); + if (ret != SQLITE_OK) { + xlog(L_WARNING, "Unable to prepare SQL query '%s': %s", new_fsidnum_by_path_sql, sqlite3_errstr(ret)); + goto out; + } + + ret = sqlite3_bind_text(stmt, 1, path, -1, NULL); + if (ret != SQLITE_OK) { + xlog(L_WARNING, "Unable to bind SQL query '%s': %s", new_fsidnum_by_path_sql, sqlite3_errstr(ret)); + goto out; + } + +again: + ret = sqlite3_step(stmt); + switch (ret) { + case SQLITE_ROW: + *fsidnum = sqlite3_column_int(stmt, 0); + success = true; + break; + case SQLITE_CONSTRAINT: + /* Maybe we lost the race against another writer and the path is now present. */ + check = 1; + break; + case SQLITE_BUSY: + case SQLITE_LOCKED: + wait_for_dbaccess(); + goto again; + default: + xlog(L_WARNING, "Error while looking up '%s' in database: %s", path, sqlite3_errstr(ret)); + } + +out: + sqlite3_finalize(stmt); + + if (check) { + bool found = false; + + get_fsidnum_by_path(path, fsidnum, &found); + if (!found) + xlog(L_WARNING, "SQLITE_CONSTRAINT error while inserting '%s' in database", path); + } + + return success; +} + +static bool sqlite_plug_fsidnum_by_path(char *path, uint32_t *fsidnum, int may_create, bool *found) +{ + bool success; + + success = get_fsidnum_by_path(path, fsidnum, found); + if (success) { + if (!*found && may_create) { + success = new_fsidnum_by_path(path, fsidnum); + if (success) + *found = true; + } + } + + return success; +} + +struct reexpdb_backend_plugin sqlite_plug_ops = { + .fsidnum_by_path = sqlite_plug_fsidnum_by_path, + .path_by_fsidnum = sqlite_plug_path_by_fsidnum, + .initdb = sqlite_plug_init, + .destroydb = sqlite_plug_destroy, +}; diff --git a/support/reexport/fsidd.c b/support/reexport/fsidd.c new file mode 100644 index 00000000..410b3a37 --- /dev/null +++ b/support/reexport/fsidd.c @@ -0,0 +1,198 @@ +#ifdef HAVE_CONFIG_H +#include +#endif + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "conffile.h" +#include "reexport_backend.h" +#include "xcommon.h" +#include "xlog.h" + +#define FSID_SOCKET_NAME "fsid.sock" + +static struct event_base *evbase; +static struct reexpdb_backend_plugin *dbbackend = &sqlite_plug_ops; + +static void client_cb(evutil_socket_t cl, short ev, void *d) +{ + struct event *me = d; + char buf[PATH_MAX * 2]; + int n; + + (void)ev; + + n = recv(cl, buf, sizeof(buf) - 1, 0); + if (n <= 0) { + event_del(me); + event_free(me); + close(cl); + return; + } + + buf[n] = '\0'; + + if (strncmp(buf, "get_fsidnum ", strlen("get_fsidnum ")) == 0) { + char *req_path = buf + strlen("get_fsidnum "); + uint32_t fsidnum; + char *answer = NULL; + bool found; + + assert(req_path < buf + n ); + + printf("client asks for %s\n", req_path); + + if (dbbackend->fsidnum_by_path(req_path, &fsidnum, false, &found)) { + if (found) + assert(asprintf(&answer, "+ %u", fsidnum) != -1); + else + assert(asprintf(&answer, "+ ") != -1); + + } else { + assert(asprintf(&answer, "- %s", "Command failed") != -1); + } + + (void)send(cl, answer, strlen(answer), 0); + + free(answer); + } else if (strncmp(buf, "get_or_create_fsidnum ", strlen("get_or_create_fsidnum ")) == 0) { + char *req_path = buf + strlen("get_or_create_fsidnum "); + uint32_t fsidnum; + char *answer = NULL; + bool found; + + assert(req_path < buf + n ); + + + if (dbbackend->fsidnum_by_path(req_path, &fsidnum, true, &found)) { + if (found) { + assert(asprintf(&answer, "+ %u", fsidnum) != -1); + } else { + assert(asprintf(&answer, "+ ") != -1); + } + + } else { + assert(asprintf(&answer, "- %s", "Command failed") != -1); + } + + (void)send(cl, answer, strlen(answer), 0); + + free(answer); + } else if (strncmp(buf, "get_path ", strlen("get_path ")) == 0) { + char *req_fsidnum = buf + strlen("get_path "); + char *path = NULL, *answer = NULL, *endp; + bool bad_input = true; + uint32_t fsidnum; + bool found; + + assert(req_fsidnum < buf + n ); + + errno = 0; + fsidnum = strtoul(req_fsidnum, &endp, 10); + if (errno == 0 && *endp == '\0') { + bad_input = false; + } + + if (bad_input) { + assert(asprintf(&answer, "- %s", "Command failed: Bad input") != -1); + } else { + if (dbbackend->path_by_fsidnum(fsidnum, &path, &found)) { + if (found) + assert(asprintf(&answer, "+ %s", path) != -1); + else + assert(asprintf(&answer, "+ ") != -1); + } else { + assert(asprintf(&answer, "+ ") != -1); + } + } + + (void)send(cl, answer, strlen(answer), 0); + + free(path); + free(answer); + } else if (strcmp(buf, "version") == 0) { + char answer[] = "+ 1"; + + (void)send(cl, answer, strlen(answer), 0); + } else { + char *answer = NULL; + + assert(asprintf(&answer, "- bad command") != -1); + (void)send(cl, answer, strlen(answer), 0); + + free(answer); + } +} + +static void srv_cb(evutil_socket_t fd, short ev, void *d) +{ + int cl = accept4(fd, NULL, NULL, SOCK_NONBLOCK); + struct event *client_ev; + + (void)ev; + (void)d; + + client_ev = event_new(evbase, cl, EV_READ | EV_PERSIST | EV_CLOSED, client_cb, event_self_cbarg()); + event_add(client_ev, NULL); +} + +int main(void) +{ + struct event *srv_ev; + struct sockaddr_un addr; + char *sock_file; + int srv; + + conf_init_file(NFS_CONFFILE); + + if (!dbbackend->initdb()) { + return 1; + } + + sock_file = conf_get_str_with_def("reexport", "fsidd_socket", FSID_SOCKET_NAME); + + unlink(sock_file); + + memset(&addr, 0, sizeof(struct sockaddr_un)); + addr.sun_family = AF_UNIX; + strncpy(addr.sun_path, sock_file, sizeof(addr.sun_path) - 1); + + srv = socket(AF_UNIX, SOCK_SEQPACKET | SOCK_NONBLOCK, 0); + if (srv == -1) { + xlog(L_WARNING, "Unable to create AF_UNIX socket for %s: %m\n", sock_file); + return 1; + } + + if (bind(srv, (const struct sockaddr *)&addr, sizeof(struct sockaddr_un)) == -1) { + xlog(L_WARNING, "Unable to bind %s: %m\n", sock_file); + return 1; + } + + if (listen(srv, 5) == -1) { + xlog(L_WARNING, "Unable to listen on %s: %m\n", sock_file); + return 1; + } + + evbase = event_base_new(); + + srv_ev = event_new(evbase, srv, EV_READ | EV_PERSIST, srv_cb, NULL); + event_add(srv_ev, NULL); + + event_base_dispatch(evbase); + + dbbackend->destroydb(); + + return 0; +} diff --git a/systemd/fsidd.service b/systemd/fsidd.service new file mode 100644 index 00000000..505a3e96 --- /dev/null +++ b/systemd/fsidd.service @@ -0,0 +1,9 @@ +[Unit] +Description=Filesystem ID service for NFS re-exporting +DefaultDependencies=no +Conflicts=umount.target +Before=nfs-server.service + +[Service] +Type=simple +ExecStart=/usr/sbin/fsidd