diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 13:46:20 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 13:46:20 +0200 |
commit | 64f29d8856a9e0d1fcdc5344f76e70c364b941cb (patch) | |
tree | 7faf56634864329b8b23d9ffdda7fa584fc3e96c /fs | |
parent | 67ed868d23711e9cec9e8adb7ae5596ae76f7cbb (diff) | |
parent | a0b3a15eab6bc2e90008460b646d53e7d9dcdbbb (diff) | |
download | linux-64f29d8856a9e0d1fcdc5344f76e70c364b941cb.tar.bz2 |
Merge tag 'ceph-for-5.17-rc1' of git://github.com/ceph/ceph-client
Pull ceph updates from Ilya Dryomov:
"The highlight is the new mount "device" string syntax implemented by
Venky Shankar. It solves some long-standing issues with using
different auth entities and/or mounting different CephFS filesystems
from the same cluster, remounting and also misleading /proc/mounts
contents. The existing syntax of course remains to be maintained.
On top of that, there is a couple of fixes for edge cases in quota and
a new mount option for turning on unbuffered I/O mode globally instead
of on a per-file basis with ioctl(CEPH_IOC_SYNCIO)"
* tag 'ceph-for-5.17-rc1' of git://github.com/ceph/ceph-client:
ceph: move CEPH_SUPER_MAGIC definition to magic.h
ceph: remove redundant Lsx caps check
ceph: add new "nopagecache" option
ceph: don't check for quotas on MDS stray dirs
ceph: drop send metrics debug message
rbd: make const pointer spaces a static const array
ceph: Fix incorrect statfs report for small quota
ceph: mount syntax module parameter
doc: document new CephFS mount device syntax
ceph: record updated mon_addr on remount
ceph: new device mount syntax
libceph: rename parse_fsid() to ceph_parse_fsid() and export
libceph: generalize addr/ip parsing based on delimiter
Diffstat (limited to 'fs')
-rw-r--r-- | fs/ceph/caps.c | 3 | ||||
-rw-r--r-- | fs/ceph/file.c | 24 | ||||
-rw-r--r-- | fs/ceph/metric.c | 2 | ||||
-rw-r--r-- | fs/ceph/quota.c | 17 | ||||
-rw-r--r-- | fs/ceph/super.c | 169 | ||||
-rw-r--r-- | fs/ceph/super.h | 28 |
6 files changed, 209 insertions, 34 deletions
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7d2c33cdbac6..7d305b974824 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3376,8 +3376,7 @@ static void handle_cap_grant(struct inode *inode, if ((newcaps & CEPH_CAP_LINK_SHARED) && (extra_info->issued & CEPH_CAP_LINK_EXCL) == 0) { set_nlink(inode, le32_to_cpu(grant->nlink)); - if (inode->i_nlink == 0 && - (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL))) + if (inode->i_nlink == 0) deleted_inode = true; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 9d9304e712d9..5b9104b8e453 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -204,6 +204,8 @@ static int ceph_init_file_info(struct inode *inode, struct file *file, int fmode, bool isdir) { struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_mount_options *opt = + ceph_inode_to_client(&ci->vfs_inode)->mount_options; struct ceph_file_info *fi; dout("%s %p %p 0%o (%s)\n", __func__, inode, file, @@ -225,6 +227,9 @@ static int ceph_init_file_info(struct inode *inode, struct file *file, if (!fi) return -ENOMEM; + if (opt->flags & CEPH_MOUNT_OPT_NOPAGECACHE) + fi->flags |= CEPH_F_SYNC; + file->private_data = fi; } @@ -1541,7 +1546,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) struct ceph_inode_info *ci = ceph_inode(inode); bool direct_lock = iocb->ki_flags & IOCB_DIRECT; ssize_t ret; - int want, got = 0; + int want = 0, got = 0; int retry_op = 0, read = 0; again: @@ -1556,13 +1561,14 @@ again: else ceph_start_io_read(inode); + if (!(fi->flags & CEPH_F_SYNC) && !direct_lock) + want |= CEPH_CAP_FILE_CACHE; if (fi->fmode & CEPH_FILE_MODE_LAZY) - want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO; - else - want = CEPH_CAP_FILE_CACHE; + want |= CEPH_CAP_FILE_LAZYIO; + ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1, &got); if (ret < 0) { - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_end_io_direct(inode); else ceph_end_io_read(inode); @@ -1696,7 +1702,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) struct ceph_osd_client *osdc = &fsc->client->osdc; struct ceph_cap_flush *prealloc_cf; ssize_t count, written = 0; - int err, want, got; + int err, want = 0, got; bool direct_lock = false; u32 map_flags; u64 pool_flags; @@ -1771,10 +1777,10 @@ retry_snap: dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n", inode, ceph_vinop(inode), pos, count, i_size_read(inode)); + if (!(fi->flags & CEPH_F_SYNC) && !direct_lock) + want |= CEPH_CAP_FILE_BUFFER; if (fi->fmode & CEPH_FILE_MODE_LAZY) - want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO; - else - want = CEPH_CAP_FILE_BUFFER; + want |= CEPH_CAP_FILE_LAZYIO; got = 0; err = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, pos + count, &got); if (err < 0) diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index c57699d8408d..0fcba68f9a99 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -160,8 +160,6 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, msg->hdr.version = cpu_to_le16(1); msg->hdr.compat_version = cpu_to_le16(1); msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); - dout("client%llu send metrics to mds%d\n", - ceph_client_gid(mdsc->fsc->client), s->s_mds); ceph_con_send(&s->s_con, msg); return true; diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 620c691af40e..a338a3ec0dc4 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -30,6 +30,9 @@ static inline bool ceph_has_realms_with_quotas(struct inode *inode) /* if root is the real CephFS root, we don't have quota realms */ if (root && ceph_ino(root) == CEPH_INO_ROOT) return false; + /* MDS stray dirs have no quota realms */ + if (ceph_vino_is_reserved(ceph_inode(inode)->i_vino)) + return false; /* otherwise, we can't know for sure */ return true; } @@ -494,10 +497,24 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) if (ci->i_max_bytes) { total = ci->i_max_bytes >> CEPH_BLOCK_SHIFT; used = ci->i_rbytes >> CEPH_BLOCK_SHIFT; + /* For quota size less than 4MB, use 4KB block size */ + if (!total) { + total = ci->i_max_bytes >> CEPH_4K_BLOCK_SHIFT; + used = ci->i_rbytes >> CEPH_4K_BLOCK_SHIFT; + buf->f_frsize = 1 << CEPH_4K_BLOCK_SHIFT; + } /* It is possible for a quota to be exceeded. * Report 'zero' in that case */ free = total > used ? total - used : 0; + /* For quota size less than 4KB, report the + * total=used=4KB,free=0 when quota is full + * and total=free=4KB, used=0 otherwise */ + if (!total) { + total = 1; + free = ci->i_max_bytes > ci->i_rbytes ? 1 : 0; + buf->f_frsize = 1 << CEPH_4K_BLOCK_SHIFT; + } } spin_unlock(&ci->i_ceph_lock); if (total) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index bea89bdb534a..bf79f369aec6 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -27,6 +27,8 @@ #include <linux/ceph/auth.h> #include <linux/ceph/debugfs.h> +#include <uapi/linux/magic.h> + static DEFINE_SPINLOCK(ceph_fsc_lock); static LIST_HEAD(ceph_fsc_list); @@ -146,6 +148,7 @@ enum { Opt_mds_namespace, Opt_recover_session, Opt_source, + Opt_mon_addr, /* string args above */ Opt_dirstat, Opt_rbytes, @@ -159,6 +162,7 @@ enum { Opt_quotadf, Opt_copyfrom, Opt_wsync, + Opt_pagecache, }; enum ceph_recover_session_mode { @@ -197,8 +201,10 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = { fsparam_u32 ("rsize", Opt_rsize), fsparam_string ("snapdirname", Opt_snapdirname), fsparam_string ("source", Opt_source), + fsparam_string ("mon_addr", Opt_mon_addr), fsparam_u32 ("wsize", Opt_wsize), fsparam_flag_no ("wsync", Opt_wsync), + fsparam_flag_no ("pagecache", Opt_pagecache), {} }; @@ -228,9 +234,92 @@ static void canonicalize_path(char *path) } /* - * Parse the source parameter. Distinguish the server list from the path. + * Check if the mds namespace in ceph_mount_options matches + * the passed in namespace string. First time match (when + * ->mds_namespace is NULL) is treated specially, since + * ->mds_namespace needs to be initialized by the caller. + */ +static int namespace_equals(struct ceph_mount_options *fsopt, + const char *namespace, size_t len) +{ + return !(fsopt->mds_namespace && + (strlen(fsopt->mds_namespace) != len || + strncmp(fsopt->mds_namespace, namespace, len))); +} + +static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end, + struct fs_context *fc) +{ + int r; + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + + if (*dev_name_end != ':') + return invalfc(fc, "separator ':' missing in source"); + + r = ceph_parse_mon_ips(dev_name, dev_name_end - dev_name, + pctx->copts, fc->log.log, ','); + if (r) + return r; + + fsopt->new_dev_syntax = false; + return 0; +} + +static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end, + struct fs_context *fc) +{ + size_t len; + struct ceph_fsid fsid; + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + char *fsid_start, *fs_name_start; + + if (*dev_name_end != '=') { + dout("separator '=' missing in source"); + return -EINVAL; + } + + fsid_start = strchr(dev_name, '@'); + if (!fsid_start) + return invalfc(fc, "missing cluster fsid"); + ++fsid_start; /* start of cluster fsid */ + + fs_name_start = strchr(fsid_start, '.'); + if (!fs_name_start) + return invalfc(fc, "missing file system name"); + + if (ceph_parse_fsid(fsid_start, &fsid)) + return invalfc(fc, "Invalid FSID"); + + ++fs_name_start; /* start of file system name */ + len = dev_name_end - fs_name_start; + + if (!namespace_equals(fsopt, fs_name_start, len)) + return invalfc(fc, "Mismatching mds_namespace"); + kfree(fsopt->mds_namespace); + fsopt->mds_namespace = kstrndup(fs_name_start, len, GFP_KERNEL); + if (!fsopt->mds_namespace) + return -ENOMEM; + dout("file system (mds namespace) '%s'\n", fsopt->mds_namespace); + + fsopt->new_dev_syntax = true; + return 0; +} + +/* + * Parse the source parameter for new device format. Distinguish the device + * spec from the path. Try parsing new device format and fallback to old + * format if needed. + * + * New device syntax will looks like: + * <device_spec>=/<path> + * where + * <device_spec> is name@fsid.fsname + * <path> is optional, but if present must begin with '/' + * (monitor addresses are passed via mount option) * - * The source will look like: + * Old device syntax is: * <server_spec>[,<server_spec>...]:[<path>] * where * <server_spec> is <ip>[:<port>] @@ -263,24 +352,44 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) dev_name_end = dev_name + strlen(dev_name); } - dev_name_end--; /* back up to ':' separator */ - if (dev_name_end < dev_name || *dev_name_end != ':') - return invalfc(fc, "No path or : separator in source"); + dev_name_end--; /* back up to separator */ + if (dev_name_end < dev_name) + return invalfc(fc, "Path missing in source"); dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); if (fsopt->server_path) dout("server path '%s'\n", fsopt->server_path); - ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name, - pctx->copts, fc->log.log); - if (ret) - return ret; + dout("trying new device syntax"); + ret = ceph_parse_new_source(dev_name, dev_name_end, fc); + if (ret) { + if (ret != -EINVAL) + return ret; + dout("trying old device syntax"); + ret = ceph_parse_old_source(dev_name, dev_name_end, fc); + if (ret) + return ret; + } fc->source = param->string; param->string = NULL; return 0; } +static int ceph_parse_mon_addr(struct fs_parameter *param, + struct fs_context *fc) +{ + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + + kfree(fsopt->mon_addr); + fsopt->mon_addr = param->string; + param->string = NULL; + + return ceph_parse_mon_ips(fsopt->mon_addr, strlen(fsopt->mon_addr), + pctx->copts, fc->log.log, '/'); +} + static int ceph_parse_mount_param(struct fs_context *fc, struct fs_parameter *param) { @@ -306,6 +415,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, param->string = NULL; break; case Opt_mds_namespace: + if (!namespace_equals(fsopt, param->string, strlen(param->string))) + return invalfc(fc, "Mismatching mds_namespace"); kfree(fsopt->mds_namespace); fsopt->mds_namespace = param->string; param->string = NULL; @@ -323,6 +434,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, if (fc->source) return invalfc(fc, "Multiple sources specified"); return ceph_parse_source(param, fc); + case Opt_mon_addr: + return ceph_parse_mon_addr(param, fc); case Opt_wsize: if (result.uint_32 < PAGE_SIZE || result.uint_32 > CEPH_MAX_WRITE_SIZE) @@ -455,6 +568,12 @@ static int ceph_parse_mount_param(struct fs_context *fc, else fsopt->flags |= CEPH_MOUNT_OPT_ASYNC_DIROPS; break; + case Opt_pagecache: + if (result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_NOPAGECACHE; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE; + break; default: BUG(); } @@ -474,6 +593,7 @@ static void destroy_mount_options(struct ceph_mount_options *args) kfree(args->mds_namespace); kfree(args->server_path); kfree(args->fscache_uniq); + kfree(args->mon_addr); kfree(args); } @@ -517,6 +637,10 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, if (ret) return ret; + ret = strcmp_null(fsopt1->mon_addr, fsopt2->mon_addr); + if (ret) + return ret; + return ceph_compare_options(new_opt, fsc->client); } @@ -572,15 +696,22 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0) seq_puts(m, ",copyfrom"); - if (fsopt->mds_namespace) + /* dump mds_namespace when old device syntax is in use */ + if (fsopt->mds_namespace && !fsopt->new_dev_syntax) seq_show_option(m, "mds_namespace", fsopt->mds_namespace); + if (fsopt->mon_addr) + seq_printf(m, ",mon_addr=%s", fsopt->mon_addr); + 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, ",wsync"); + if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE) + seq_puts(m, ",nopagecache"); + if (fsopt->wsize != CEPH_MAX_WRITE_SIZE) seq_printf(m, ",wsize=%u", fsopt->wsize); if (fsopt->rsize != CEPH_MAX_READ_SIZE) @@ -1052,6 +1183,7 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) static int ceph_get_tree(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; struct super_block *sb; struct ceph_fs_client *fsc; struct dentry *res; @@ -1063,6 +1195,8 @@ static int ceph_get_tree(struct fs_context *fc) if (!fc->source) return invalfc(fc, "No source"); + if (fsopt->new_dev_syntax && !fsopt->mon_addr) + return invalfc(fc, "No monitor address"); /* create client (which we may/may not use) */ fsc = create_fs_client(pctx->opts, pctx->copts); @@ -1148,6 +1282,13 @@ static int ceph_reconfigure_fc(struct fs_context *fc) else ceph_clear_mount_opt(fsc, ASYNC_DIROPS); + if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) { + kfree(fsc->mount_options->mon_addr); + fsc->mount_options->mon_addr = fsopt->mon_addr; + fsopt->mon_addr = NULL; + pr_notice("ceph: monitor addresses recorded, but not used for reconnection"); + } + sync_filesystem(fc->root->d_sb); return 0; } @@ -1325,6 +1466,14 @@ bool disable_send_metrics = false; module_param_cb(disable_send_metrics, ¶m_ops_metrics, &disable_send_metrics, 0644); MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)"); +/* for both v1 and v2 syntax */ +static bool mount_support = true; +static const struct kernel_param_ops param_ops_mount_syntax = { + .get = param_get_bool, +}; +module_param_cb(mount_syntax_v1, ¶m_ops_mount_syntax, &mount_support, 0444); +module_param_cb(mount_syntax_v2, ¶m_ops_mount_syntax, &mount_support, 0444); + module_init(init_ceph); module_exit(exit_ceph); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index d0142cc5c41b..67f145e1ae7a 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -24,13 +24,11 @@ #include <linux/fscache.h> #endif -/* f_type in struct statfs */ -#define CEPH_SUPER_MAGIC 0x00c36400 - /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */ #define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT) +#define CEPH_4K_BLOCK_SHIFT 12 /* 4 KB */ #define CEPH_MOUNT_OPT_CLEANRECOVER (1<<1) /* auto reonnect (clean mode) after blocklisted */ #define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */ @@ -44,6 +42,7 @@ #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_NOPAGECACHE (1<<16) /* bypass pagecache altogether */ #define CEPH_MOUNT_OPT_DEFAULT \ (CEPH_MOUNT_OPT_DCACHE | \ @@ -88,6 +87,8 @@ struct ceph_mount_options { unsigned int max_readdir; /* max readdir result (entries) */ unsigned int max_readdir_bytes; /* max readdir result (bytes) */ + bool new_dev_syntax; + /* * everything above this point can be memcmp'd; everything below * is handled in compare_mount_options() @@ -97,6 +98,7 @@ struct ceph_mount_options { char *mds_namespace; /* default NULL */ char *server_path; /* default NULL (means "/") */ char *fscache_uniq; /* default NULL */ + char *mon_addr; }; struct ceph_fs_client { @@ -534,19 +536,23 @@ static inline int ceph_ino_compare(struct inode *inode, void *data) * * These come from src/mds/mdstypes.h in the ceph sources. */ -#define CEPH_MAX_MDS 0x100 -#define CEPH_NUM_STRAY 10 +#define CEPH_MAX_MDS 0x100 +#define CEPH_NUM_STRAY 10 #define CEPH_MDS_INO_MDSDIR_OFFSET (1 * CEPH_MAX_MDS) +#define CEPH_MDS_INO_LOG_OFFSET (2 * CEPH_MAX_MDS) #define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY)) static inline bool ceph_vino_is_reserved(const struct ceph_vino vino) { - if (vino.ino < CEPH_INO_SYSTEM_BASE && - vino.ino >= CEPH_MDS_INO_MDSDIR_OFFSET) { - WARN_RATELIMIT(1, "Attempt to access reserved inode number 0x%llx", vino.ino); - return true; - } - return false; + if (vino.ino >= CEPH_INO_SYSTEM_BASE || + vino.ino < CEPH_MDS_INO_MDSDIR_OFFSET) + return false; + + /* Don't warn on mdsdirs */ + WARN_RATELIMIT(vino.ino >= CEPH_MDS_INO_LOG_OFFSET, + "Attempt to access reserved inode number 0x%llx", + vino.ino); + return true; } static inline struct inode *ceph_find_inode(struct super_block *sb, |