Resguardo inicial

linux-7.2.3/fs/ceph/Kconfig

@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config CEPH_FS
+	tristate "Ceph distributed file system"
+	depends on INET
+	select CEPH_LIB
+	select NETFS_SUPPORT
+	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
+	default n
+	help
+	  Choose Y or M here to include support for mounting the
+	  experimental Ceph distributed file system.  Ceph is an extremely
+	  scalable file system designed to provide high performance,
+	  reliable access to petabytes of storage.
+
+	  More information at https://ceph.io/.
+
+	  If unsure, say N.
+
+if CEPH_FS
+config CEPH_FSCACHE
+	bool "Enable Ceph client caching support"
+	depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y
+	help
+	  Choose Y here to enable persistent, read-only local
+	  caching support for Ceph clients using FS-Cache
+
+endif
+
+config CEPH_FS_POSIX_ACL
+	bool "Ceph POSIX Access Control Lists"
+	depends on CEPH_FS
+	select FS_POSIX_ACL
+	help
+	  POSIX Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  If you don't know what Access Control Lists are, say N
+
+config CEPH_FS_SECURITY_LABEL
+	bool "CephFS Security Labels"
+	depends on CEPH_FS && SECURITY
+	help
+	  Security labels support alternative access control models
+	  implemented by security modules like SELinux. This option
+	  enables an extended attribute handler for file security
+	  labels in the Ceph filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.

linux-7.2.3/fs/ceph/Makefile

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for CEPH filesystem.
+#
+
+obj-$(CONFIG_CEPH_FS) += ceph.o
+
+ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
+	export.o caps.o snap.o xattr.o quota.o io.o \
+	mds_client.o mdsmap.o strings.o ceph_frag.o \
+	debugfs.o util.o metric.o subvolume_metrics.o
+
+ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
+ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o
+ceph-$(CONFIG_FS_ENCRYPTION) += crypto.o

linux-7.2.3/fs/ceph/acl.c

@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/fs/ceph/acl.c
+ *
+ * Copyright (C) 2013 Guangliang Zhao, <lucienchao@gmail.com>
+ */
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include "super.h"
+#include "mds_client.h"
+
+static inline void ceph_set_cached_acl(struct inode *inode,
+					int type, struct posix_acl *acl)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 0))
+		set_cached_acl(inode, type, acl);
+	else
+		forget_cached_acl(inode, type);
+	spin_unlock(&ci->i_ceph_lock);
+}
+
+struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int size;
+	unsigned int retry_cnt = 0;
+	const char *name;
+	char *value = NULL;
+	struct posix_acl *acl;
+
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+
+retry:
+	size = __ceph_getxattr(inode, name, "", 0);
+	if (size > 0) {
+		value = kzalloc(size, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		size = __ceph_getxattr(inode, name, value, size);
+	}
+
+	if (size == -ERANGE && retry_cnt < 10) {
+		retry_cnt++;
+		kfree(value);
+		value = NULL;
+		goto retry;
+	}
+
+	if (size > 0) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+	} else if (size == -ENODATA || size == 0) {
+		acl = NULL;
+	} else {
+		pr_err_ratelimited_client(cl, "%llx.%llx failed, err=%d\n",
+					  ceph_vinop(inode), size);
+		acl = ERR_PTR(-EIO);
+	}
+
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		ceph_set_cached_acl(inode, type, acl);
+
+	return acl;
+}
+
+int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		 struct posix_acl *acl, int type)
+{
+	int ret = 0;
+	size_t size = 0;
+	const char *name = NULL;
+	char *value = NULL;
+	struct iattr newattrs;
+	struct inode *inode = d_inode(dentry);
+	struct timespec64 old_ctime = inode_get_ctime(inode);
+	umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP) {
+		ret = -EROFS;
+		goto out;
+	}
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
+		if (acl) {
+			ret = posix_acl_update_mode(idmap, inode,
+						    &new_mode, &acl);
+			if (ret)
+				goto out;
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		if (!S_ISDIR(inode->i_mode)) {
+			ret = acl ? -EINVAL : 0;
+			goto out;
+		}
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (acl) {
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_NOFS);
+		if (!value) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	if (new_mode != old_mode) {
+		newattrs.ia_ctime = current_time(inode);
+		newattrs.ia_mode = new_mode;
+		newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
+		ret = __ceph_setattr(idmap, inode, &newattrs, NULL);
+		if (ret)
+			goto out_free;
+	}
+
+	ret = __ceph_setxattr(inode, name, value, size, 0);
+	if (ret) {
+		if (new_mode != old_mode) {
+			newattrs.ia_ctime = old_ctime;
+			newattrs.ia_mode = old_mode;
+			newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
+			__ceph_setattr(idmap, inode, &newattrs, NULL);
+		}
+		goto out_free;
+	}
+
+	ceph_set_cached_acl(inode, type, acl);
+
+out_free:
+	kfree(value);
+out:
+	return ret;
+}
+
+int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
+		       struct ceph_acl_sec_ctx *as_ctx)
+{
+	struct posix_acl *acl, *default_acl;
+	size_t val_size1 = 0, val_size2 = 0;
+	struct ceph_pagelist *pagelist = NULL;
+	void *tmp_buf1 = NULL, *tmp_buf2 = NULL;
+	int err;
+
+	err = posix_acl_create(dir, mode, &default_acl, &acl);
+	if (err)
+		return err;
+
+	if (acl) {
+		err = posix_acl_equiv_mode(acl, mode);
+		if (err < 0)
+			goto out_err;
+		if (err == 0) {
+			posix_acl_release(acl);
+			acl = NULL;
+		}
+	}
+
+	if (!default_acl && !acl)
+		return 0;
+
+	err = -ENOMEM;
+	pagelist = ceph_pagelist_alloc(GFP_KERNEL);
+	if (!pagelist)
+		goto out_err;
+
+	err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
+	if (err)
+		goto out_err;
+
+	ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
+
+	if (acl) {
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
+
+		err = -ENOMEM;
+		tmp_buf1 = posix_acl_to_xattr(&init_user_ns, acl,
+					      &val_size1, GFP_KERNEL);
+		if (!tmp_buf1)
+			goto out_err;
+		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
+		if (err)
+			goto out_err;
+		ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
+					    len);
+		ceph_pagelist_encode_32(pagelist, val_size1);
+		ceph_pagelist_append(pagelist, tmp_buf1, val_size1);
+	}
+	if (default_acl) {
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
+
+		err = -ENOMEM;
+		tmp_buf2 = posix_acl_to_xattr(&init_user_ns, default_acl,
+					      &val_size2, GFP_KERNEL);
+		if (!tmp_buf2)
+			goto out_err;
+		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
+		if (err)
+			goto out_err;
+		ceph_pagelist_encode_string(pagelist,
+					  XATTR_NAME_POSIX_ACL_DEFAULT, len);
+		ceph_pagelist_encode_32(pagelist, val_size2);
+		ceph_pagelist_append(pagelist, tmp_buf2, val_size2);
+	}
+
+	kfree(tmp_buf1);
+	kfree(tmp_buf2);
+
+	as_ctx->acl = acl;
+	as_ctx->default_acl = default_acl;
+	as_ctx->pagelist = pagelist;
+	return 0;
+
+out_err:
+	posix_acl_release(acl);
+	posix_acl_release(default_acl);
+	kfree(tmp_buf1);
+	kfree(tmp_buf2);
+	if (pagelist)
+		ceph_pagelist_release(pagelist);
+	return err;
+}
+
+void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx)
+{
+	if (!inode)
+		return;
+	ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, as_ctx->acl);
+	ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, as_ctx->default_acl);
+}

linux-7.2.3/fs/ceph/cache.c

@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Ceph cache definitions.
+ *
+ *  Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
+ *  Written by Milosz Tanski (milosz@adfin.com)
+ */
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/fs_context.h>
+#include "super.h"
+#include "cache.h"
+
+void ceph_fscache_register_inode_cookie(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+
+	/* No caching for filesystem? */
+	if (!fsc->fscache)
+		return;
+
+	/* Regular files only */
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	/* Only new inodes! */
+	if (!(inode_state_read_once(inode) & I_NEW))
+		return;
+
+	WARN_ON_ONCE(ci->netfs.cache);
+
+	ci->netfs.cache =
+		fscache_acquire_cookie(fsc->fscache, 0,
+				       &ci->i_vino, sizeof(ci->i_vino),
+				       &ci->i_version, sizeof(ci->i_version),
+				       i_size_read(inode));
+	if (ci->netfs.cache)
+		mapping_set_release_always(inode->i_mapping);
+}
+
+void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci)
+{
+	fscache_relinquish_cookie(ceph_fscache_cookie(ci), false);
+}
+
+void ceph_fscache_use_cookie(struct inode *inode, bool will_modify)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	fscache_use_cookie(ceph_fscache_cookie(ci), will_modify);
+}
+
+void ceph_fscache_unuse_cookie(struct inode *inode, bool update)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	if (update) {
+		loff_t i_size = i_size_read(inode);
+
+		fscache_unuse_cookie(ceph_fscache_cookie(ci),
+				     &ci->i_version, &i_size);
+	} else {
+		fscache_unuse_cookie(ceph_fscache_cookie(ci), NULL, NULL);
+	}
+}
+
+void ceph_fscache_update(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	loff_t i_size = i_size_read(inode);
+
+	fscache_update_cookie(ceph_fscache_cookie(ci), &ci->i_version, &i_size);
+}
+
+void ceph_fscache_invalidate(struct inode *inode, bool dio_write)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	fscache_invalidate(ceph_fscache_cookie(ci),
+			   &ci->i_version, i_size_read(inode),
+			   dio_write ? FSCACHE_INVAL_DIO_WRITE : 0);
+}
+
+int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc)
+{
+	const struct ceph_fsid *fsid = &fsc->client->fsid;
+	const char *fscache_uniq = fsc->mount_options->fscache_uniq;
+	size_t uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0;
+	char *name;
+	int err = 0;
+
+	name = kasprintf(GFP_KERNEL, "ceph,%pU%s%s", fsid, uniq_len ? "," : "",
+			 uniq_len ? fscache_uniq : "");
+	if (!name)
+		return -ENOMEM;
+
+	fsc->fscache = fscache_acquire_volume(name, NULL, NULL, 0);
+	if (IS_ERR_OR_NULL(fsc->fscache)) {
+		errorfc(fc, "Unable to register fscache cookie for %s", name);
+		err = fsc->fscache ? PTR_ERR(fsc->fscache) : -EOPNOTSUPP;
+		fsc->fscache = NULL;
+	}
+	kfree(name);
+	return err;
+}
+
+void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
+{
+	fscache_relinquish_volume(fsc->fscache, NULL, false);
+}

linux-7.2.3/fs/ceph/cache.h

@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Ceph cache definitions.
+ *
+ *  Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
+ *  Written by Milosz Tanski (milosz@adfin.com)
+ */
+
+#ifndef _CEPH_CACHE_H
+#define _CEPH_CACHE_H
+
+#include <linux/netfs.h>
+
+#ifdef CONFIG_CEPH_FSCACHE
+#include <linux/fscache.h>
+
+int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc);
+void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
+
+void ceph_fscache_register_inode_cookie(struct inode *inode);
+void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci);
+
+void ceph_fscache_use_cookie(struct inode *inode, bool will_modify);
+void ceph_fscache_unuse_cookie(struct inode *inode, bool update);
+
+void ceph_fscache_update(struct inode *inode);
+void ceph_fscache_invalidate(struct inode *inode, bool dio_write);
+
+static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
+{
+	return netfs_i_cookie(&ci->netfs);
+}
+
+static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct fscache_cookie *cookie = ceph_fscache_cookie(ci);
+
+	if (cookie) {
+		ceph_fscache_use_cookie(inode, true);
+		fscache_resize_cookie(cookie, to);
+		ceph_fscache_unuse_cookie(inode, true);
+	}
+}
+
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
+						struct writeback_control *wbc)
+{
+	return netfs_unpin_writeback(inode, wbc);
+}
+
+#define ceph_fscache_dirty_folio netfs_dirty_folio
+
+static inline bool ceph_is_cache_enabled(struct inode *inode)
+{
+	return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode)));
+}
+
+#else /* CONFIG_CEPH_FSCACHE */
+static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc,
+					   struct fs_context *fc)
+{
+	return 0;
+}
+
+static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
+{
+}
+
+static inline void ceph_fscache_register_inode_cookie(struct inode *inode)
+{
+}
+
+static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
+{
+}
+
+static inline void ceph_fscache_use_cookie(struct inode *inode, bool will_modify)
+{
+}
+
+static inline void ceph_fscache_unuse_cookie(struct inode *inode, bool update)
+{
+}
+
+static inline void ceph_fscache_update(struct inode *inode)
+{
+}
+
+static inline void ceph_fscache_invalidate(struct inode *inode, bool dio_write)
+{
+}
+
+static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
+{
+	return NULL;
+}
+
+static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
+{
+}
+
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
+					       struct writeback_control *wbc)
+{
+	return 0;
+}
+
+#define ceph_fscache_dirty_folio filemap_dirty_folio
+
+static inline bool ceph_is_cache_enabled(struct inode *inode)
+{
+	return false;
+}
+#endif /* CONFIG_CEPH_FSCACHE */
+
+#endif

linux-7.2.3/fs/ceph/ceph_frag.c

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ceph 'frag' type
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+int ceph_frag_compare(__u32 a, __u32 b)
+{
+	unsigned va = ceph_frag_value(a);
+	unsigned vb = ceph_frag_value(b);
+	if (va < vb)
+		return -1;
+	if (va > vb)
+		return 1;
+	va = ceph_frag_bits(a);
+	vb = ceph_frag_bits(b);
+	if (va < vb)
+		return -1;
+	if (va > vb)
+		return 1;
+	return 0;
+}

linux-7.2.3/fs/ceph/crypto.c

@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * The base64 encode/decode code was copied from fscrypt:
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ * Written by Uday Savagaonkar, 2014.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+#include <linux/ceph/ceph_debug.h>
+#include <linux/xattr.h>
+#include <linux/fscrypt.h>
+#include <linux/ceph/striper.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include "crypto.h"
+
+static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fscrypt_auth *cfa = (struct ceph_fscrypt_auth *)ci->fscrypt_auth;
+	u32 ctxlen;
+
+	/* Non existent or too short? */
+	if (!cfa || (ci->fscrypt_auth_len < (offsetof(struct ceph_fscrypt_auth, cfa_blob) + 1)))
+		return -ENOBUFS;
+
+	/* Some format we don't recognize? */
+	if (le32_to_cpu(cfa->cfa_version) != CEPH_FSCRYPT_AUTH_VERSION)
+		return -ENOBUFS;
+
+	ctxlen = le32_to_cpu(cfa->cfa_blob_len);
+	if (len < ctxlen)
+		return -ERANGE;
+
+	memcpy(ctx, cfa->cfa_blob, ctxlen);
+	return ctxlen;
+}
+
+static int ceph_crypt_set_context(struct inode *inode, const void *ctx,
+				  size_t len, void *fs_data)
+{
+	int ret;
+	struct iattr attr = { };
+	struct ceph_iattr cia = { };
+	struct ceph_fscrypt_auth *cfa;
+
+	WARN_ON_ONCE(fs_data);
+
+	if (len > FSCRYPT_SET_CONTEXT_MAX_SIZE)
+		return -EINVAL;
+
+	cfa = kzalloc_obj(*cfa);
+	if (!cfa)
+		return -ENOMEM;
+
+	cfa->cfa_version = cpu_to_le32(CEPH_FSCRYPT_AUTH_VERSION);
+	cfa->cfa_blob_len = cpu_to_le32(len);
+	memcpy(cfa->cfa_blob, ctx, len);
+
+	cia.fscrypt_auth = cfa;
+
+	ret = __ceph_setattr(&nop_mnt_idmap, inode, &attr, &cia);
+	if (ret == 0)
+		inode_set_flags(inode, S_ENCRYPTED, S_ENCRYPTED);
+	kfree(cia.fscrypt_auth);
+	return ret;
+}
+
+static bool ceph_crypt_empty_dir(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	return ci->i_rsubdirs + ci->i_rfiles == 1;
+}
+
+static const union fscrypt_policy *ceph_get_dummy_policy(struct super_block *sb)
+{
+	return ceph_sb_to_fs_client(sb)->fsc_dummy_enc_policy.policy;
+}
+
+static struct fscrypt_operations ceph_fscrypt_ops = {
+	.inode_info_offs	= (int)offsetof(struct ceph_inode_info, i_crypt_info) -
+				  (int)offsetof(struct ceph_inode_info, netfs.inode),
+	.needs_bounce_pages	= 1,
+	.get_context		= ceph_crypt_get_context,
+	.set_context		= ceph_crypt_set_context,
+	.get_dummy_policy	= ceph_get_dummy_policy,
+	.empty_dir		= ceph_crypt_empty_dir,
+};
+
+void ceph_fscrypt_set_ops(struct super_block *sb)
+{
+	fscrypt_set_ops(sb, &ceph_fscrypt_ops);
+}
+
+void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc)
+{
+	fscrypt_free_dummy_policy(&fsc->fsc_dummy_enc_policy);
+}
+
+int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+				 struct ceph_acl_sec_ctx *as)
+{
+	int ret, ctxsize;
+	bool encrypted = false;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ret = fscrypt_prepare_new_inode(dir, inode, &encrypted);
+	if (ret)
+		return ret;
+	if (!encrypted)
+		return 0;
+
+	as->fscrypt_auth = kzalloc_obj(*as->fscrypt_auth);
+	if (!as->fscrypt_auth)
+		return -ENOMEM;
+
+	ctxsize = fscrypt_context_for_new_inode(as->fscrypt_auth->cfa_blob,
+						inode);
+	if (ctxsize < 0)
+		return ctxsize;
+
+	as->fscrypt_auth->cfa_version = cpu_to_le32(CEPH_FSCRYPT_AUTH_VERSION);
+	as->fscrypt_auth->cfa_blob_len = cpu_to_le32(ctxsize);
+
+	WARN_ON_ONCE(ci->fscrypt_auth);
+	kfree(ci->fscrypt_auth);
+	ci->fscrypt_auth_len = ceph_fscrypt_auth_len(as->fscrypt_auth);
+	ci->fscrypt_auth = kmemdup(as->fscrypt_auth, ci->fscrypt_auth_len,
+				   GFP_KERNEL);
+	if (!ci->fscrypt_auth)
+		return -ENOMEM;
+
+	inode->i_flags |= S_ENCRYPTED;
+
+	return 0;
+}
+
+void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+				struct ceph_acl_sec_ctx *as)
+{
+	swap(req->r_fscrypt_auth, as->fscrypt_auth);
+}
+
+/*
+ * User-created snapshots can't start with '_'.  Snapshots that start with this
+ * character are special (hint: there aren't real snapshots) and use the
+ * following format:
+ *
+ *   _<SNAPSHOT-NAME>_<INODE-NUMBER>
+ *
+ * where:
+ *  - <SNAPSHOT-NAME> - the real snapshot name that may need to be decrypted,
+ *  - <INODE-NUMBER> - the inode number (in decimal) for the actual snapshot
+ *
+ * This function parses these snapshot names and returns the inode
+ * <INODE-NUMBER>.  'name_len' will also bet set with the <SNAPSHOT-NAME>
+ * length.
+ */
+static struct inode *parse_longname(const struct inode *parent,
+				    const char *name, int *name_len)
+{
+	struct ceph_client *cl = ceph_inode_to_client(parent);
+	struct inode *dir = NULL;
+	struct ceph_vino vino = { .snap = CEPH_NOSNAP };
+	char *name_end, *inode_number;
+	int ret = -EIO;
+	/* Snapshot name must start with an underscore */
+	if (*name_len <= 0 || name[0] != '_')
+		return ERR_PTR(-EIO);
+	/* Skip initial '_' and NUL-terminate */
+	char *str __free(kfree) = kmemdup_nul(name + 1, *name_len - 1, GFP_KERNEL);
+	if (!str)
+		return ERR_PTR(-ENOMEM);
+	name_end = strrchr(str, '_');
+	if (!name_end) {
+		doutc(cl, "failed to parse long snapshot name: %s\n", str);
+		return ERR_PTR(-EIO);
+	}
+	*name_len = (name_end - str);
+	if (*name_len <= 0) {
+		pr_err_client(cl, "failed to parse long snapshot name\n");
+		return ERR_PTR(-EIO);
+	}
+
+	/* Get the inode number */
+	inode_number = name_end + 1;
+	ret = kstrtou64(inode_number, 10, &vino.ino);
+	if (ret) {
+		doutc(cl, "failed to parse inode number: %s\n", str);
+		return ERR_PTR(ret);
+	}
+
+	/* And finally the inode */
+	dir = ceph_find_inode(parent->i_sb, vino);
+	if (!dir) {
+		/* This can happen if we're not mounting cephfs on the root */
+		dir = ceph_get_inode(parent->i_sb, vino, NULL);
+		if (IS_ERR(dir))
+			doutc(cl, "can't find inode %s (%s)\n", inode_number, name);
+	}
+	return dir;
+}
+
+int ceph_encode_encrypted_dname(struct inode *parent, char *buf, int elen)
+{
+	struct ceph_client *cl = ceph_inode_to_client(parent);
+	struct inode *dir = parent;
+	char *p = buf;
+	u32 len;
+	int name_len = elen;
+	int ret;
+	u8 *cryptbuf = NULL;
+
+	/* Handle the special case of snapshot names that start with '_' */
+	if (ceph_snap(dir) == CEPH_SNAPDIR && *p == '_') {
+		dir = parse_longname(parent, p, &name_len);
+		if (IS_ERR(dir))
+			return PTR_ERR(dir);
+		p++; /* skip initial '_' */
+	}
+
+	if (!fscrypt_has_encryption_key(dir))
+		goto out;
+
+	/*
+	 * Convert cleartext d_name to ciphertext. If result is longer than
+	 * CEPH_NOHASH_NAME_MAX, sha256 the remaining bytes
+	 *
+	 * See: fscrypt_setup_filename
+	 */
+	if (!fscrypt_fname_encrypted_size(dir, name_len, NAME_MAX, &len)) {
+		elen = -ENAMETOOLONG;
+		goto out;
+	}
+
+	/* Allocate a buffer appropriate to hold the result */
+	cryptbuf = kmalloc(len > CEPH_NOHASH_NAME_MAX ? NAME_MAX : len,
+			   GFP_KERNEL);
+	if (!cryptbuf) {
+		elen = -ENOMEM;
+		goto out;
+	}
+
+	ret = fscrypt_fname_encrypt(dir,
+				    &(struct qstr)QSTR_INIT(p, name_len),
+				    cryptbuf, len);
+	if (ret) {
+		elen = ret;
+		goto out;
+	}
+
+	/* hash the end if the name is long enough */
+	if (len > CEPH_NOHASH_NAME_MAX) {
+		u8 hash[SHA256_DIGEST_SIZE];
+		u8 *extra = cryptbuf + CEPH_NOHASH_NAME_MAX;
+
+		/*
+		 * hash the extra bytes and overwrite crypttext beyond that
+		 * point with it
+		 */
+		sha256(extra, len - CEPH_NOHASH_NAME_MAX, hash);
+		memcpy(extra, hash, SHA256_DIGEST_SIZE);
+		len = CEPH_NOHASH_NAME_MAX + SHA256_DIGEST_SIZE;
+	}
+
+	/* base64 encode the encrypted name */
+	elen = base64_encode(cryptbuf, len, p, false, BASE64_IMAP);
+	doutc(cl, "base64-encoded ciphertext name = %.*s\n", elen, p);
+
+	/* To understand the 240 limit, see CEPH_NOHASH_NAME_MAX comments */
+	WARN_ON(elen > 240);
+	if (dir != parent) // leading _ is already there; append _<inum>
+		elen += 1 + sprintf(p + elen, "_%llu", dir->i_ino);
+
+out:
+	kfree(cryptbuf);
+	if (dir != parent) {
+		if ((inode_state_read_once(dir) & I_NEW))
+			discard_new_inode(dir);
+		else
+			iput(dir);
+	}
+	return elen;
+}
+
+/**
+ * ceph_fname_to_usr - convert a filename for userland presentation
+ * @fname: ceph_fname to be converted
+ * @tname: temporary name buffer to use for conversion (may be NULL)
+ * @oname: where converted name should be placed
+ * @is_nokey: set to true if key wasn't available during conversion (may be NULL)
+ *
+ * Given a filename (usually from the MDS), format it for presentation to
+ * userland. If @parent is not encrypted, just pass it back as-is.
+ *
+ * Otherwise, base64 decode the string, and then ask fscrypt to format it
+ * for userland presentation.
+ *
+ * Returns 0 on success or negative error code on error.
+ */
+int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
+		      struct fscrypt_str *oname, bool *is_nokey)
+{
+	struct inode *dir = fname->dir;
+	struct fscrypt_str _tname = FSTR_INIT(NULL, 0);
+	struct fscrypt_str iname;
+	char *name = fname->name;
+	int name_len = fname->name_len;
+	int ret;
+
+	/* Sanity check that the resulting name will fit in the buffer */
+	if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX)
+		return -EIO;
+
+	/* Handle the special case of snapshot names that start with '_' */
+	if ((ceph_snap(dir) == CEPH_SNAPDIR) && (name_len > 0) &&
+	    (name[0] == '_')) {
+		dir = parse_longname(dir, name, &name_len);
+		if (IS_ERR(dir))
+			return PTR_ERR(dir);
+		name++; /* skip initial '_' */
+	}
+
+	if (!IS_ENCRYPTED(dir)) {
+		oname->name = fname->name;
+		oname->len = fname->name_len;
+		ret = 0;
+		goto out_inode;
+	}
+
+	ret = ceph_fscrypt_prepare_readdir(dir);
+	if (ret)
+		goto out_inode;
+
+	/*
+	 * Use the raw dentry name as sent by the MDS instead of
+	 * generating a nokey name via fscrypt.
+	 */
+	if (!fscrypt_has_encryption_key(dir)) {
+		if (fname->no_copy)
+			oname->name = fname->name;
+		else
+			memcpy(oname->name, fname->name, fname->name_len);
+		oname->len = fname->name_len;
+		if (is_nokey)
+			*is_nokey = true;
+		ret = 0;
+		goto out_inode;
+	}
+
+	if (fname->ctext_len == 0) {
+		int declen;
+
+		if (!tname) {
+			ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname);
+			if (ret)
+				goto out_inode;
+			tname = &_tname;
+		}
+
+		declen = base64_decode(name, name_len,
+				       tname->name, false, BASE64_IMAP);
+		if (declen <= 0) {
+			ret = -EIO;
+			goto out;
+		}
+		iname.name = tname->name;
+		iname.len = declen;
+	} else {
+		iname.name = fname->ctext;
+		iname.len = fname->ctext_len;
+	}
+
+	ret = fscrypt_fname_disk_to_usr(dir, 0, 0, &iname, oname);
+	if (!ret && (dir != fname->dir)) {
+		char tmp_buf[BASE64_CHARS(NAME_MAX)];
+
+		name_len = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%llu",
+				    oname->len, oname->name, dir->i_ino);
+		memcpy(oname->name, tmp_buf, name_len);
+		oname->len = name_len;
+	}
+
+out:
+	fscrypt_fname_free_buffer(&_tname);
+out_inode:
+	if (dir != fname->dir) {
+		if ((inode_state_read_once(dir) & I_NEW))
+			discard_new_inode(dir);
+		else
+			iput(dir);
+	}
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_prepare_readdir - simple __fscrypt_prepare_readdir() wrapper
+ * @dir: directory inode for readdir prep
+ *
+ * Simple wrapper around __fscrypt_prepare_readdir() that will mark directory as
+ * non-complete if this call results in having the directory unlocked.
+ *
+ * Returns:
+ *     1 - if directory was locked and key is now loaded (i.e. dir is unlocked)
+ *     0 - if directory is still locked
+ *   < 0 - if __fscrypt_prepare_readdir() fails
+ */
+int ceph_fscrypt_prepare_readdir(struct inode *dir)
+{
+	bool had_key = fscrypt_has_encryption_key(dir);
+	int err;
+
+	if (!IS_ENCRYPTED(dir))
+		return 0;
+
+	err = __fscrypt_prepare_readdir(dir);
+	if (err)
+		return err;
+	if (!had_key && fscrypt_has_encryption_key(dir)) {
+		/* directory just got unlocked, mark it as not complete */
+		ceph_dir_clear_complete(dir);
+		return 1;
+	}
+	return 0;
+}
+
+int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
+	doutc(cl, "%p %llx.%llx len %u offs %u blk %llu\n", inode,
+	      ceph_vinop(inode), len, offs, lblk_num);
+	return fscrypt_decrypt_block_inplace(inode, page, len, offs, lblk_num);
+}
+
+int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
+	doutc(cl, "%p %llx.%llx len %u offs %u blk %llu\n", inode,
+	      ceph_vinop(inode), len, offs, lblk_num);
+	return fscrypt_encrypt_block_inplace(inode, page, len, offs, lblk_num);
+}
+
+/**
+ * ceph_fscrypt_decrypt_pages - decrypt an array of pages
+ * @inode: pointer to inode associated with these pages
+ * @page: pointer to page array
+ * @off: offset into the file that the read data starts
+ * @len: max length to decrypt
+ *
+ * Decrypt an array of fscrypt'ed pages and return the amount of
+ * data decrypted. Any data in the page prior to the start of the
+ * first complete block in the read is ignored. Any incomplete
+ * crypto blocks at the end of the array are ignored (and should
+ * probably be zeroed by the caller).
+ *
+ * Returns the length of the decrypted data or a negative errno.
+ */
+int ceph_fscrypt_decrypt_pages(struct inode *inode, struct page **page,
+			       u64 off, int len)
+{
+	int i, num_blocks;
+	u64 baseblk = off >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	int ret = 0;
+
+	/*
+	 * We can't deal with partial blocks on an encrypted file, so mask off
+	 * the last bit.
+	 */
+	num_blocks = ceph_fscrypt_blocks(off, len & CEPH_FSCRYPT_BLOCK_MASK);
+
+	/* Decrypt each block */
+	for (i = 0; i < num_blocks; ++i) {
+		int blkoff = i << CEPH_FSCRYPT_BLOCK_SHIFT;
+		int pgidx = blkoff >> PAGE_SHIFT;
+		unsigned int pgoffs = offset_in_page(blkoff);
+		int fret;
+
+		fret = ceph_fscrypt_decrypt_block_inplace(inode, page[pgidx],
+				CEPH_FSCRYPT_BLOCK_SIZE, pgoffs,
+				baseblk + i);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret += CEPH_FSCRYPT_BLOCK_SIZE;
+	}
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_decrypt_extents: decrypt received extents in given buffer
+ * @inode: inode associated with pages being decrypted
+ * @page: pointer to page array
+ * @off: offset into the file that the data in page[0] starts
+ * @map: pointer to extent array
+ * @ext_cnt: length of extent array
+ *
+ * Given an extent map and a page array, decrypt the received data in-place,
+ * skipping holes. Returns the offset into buffer of end of last decrypted
+ * block.
+ */
+int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
+				 u64 off, struct ceph_sparse_extent *map,
+				 u32 ext_cnt)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int i, ret = 0;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 objno, objoff;
+	u32 xlen;
+
+	/* Nothing to do for empty array */
+	if (ext_cnt == 0) {
+		doutc(cl, "%p %llx.%llx empty array, ret 0\n", inode,
+		      ceph_vinop(inode));
+		return 0;
+	}
+
+	ceph_calc_file_object_mapping(&ci->i_layout, off, map[0].len,
+				      &objno, &objoff, &xlen);
+
+	for (i = 0; i < ext_cnt; ++i) {
+		struct ceph_sparse_extent *ext = &map[i];
+		int pgsoff = ext->off - objoff;
+		int pgidx = pgsoff >> PAGE_SHIFT;
+		int fret;
+
+		if ((ext->off | ext->len) & ~CEPH_FSCRYPT_BLOCK_MASK) {
+			pr_warn_client(cl,
+				"%p %llx.%llx bad encrypted sparse extent "
+				"idx %d off %llx len %llx\n",
+				inode, ceph_vinop(inode), i, ext->off,
+				ext->len);
+			return -EIO;
+		}
+		fret = ceph_fscrypt_decrypt_pages(inode, &page[pgidx],
+						 off + pgsoff, ext->len);
+		doutc(cl, "%p %llx.%llx [%d] 0x%llx~0x%llx fret %d\n", inode,
+		      ceph_vinop(inode), i, ext->off, ext->len, fret);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret = pgsoff + fret;
+	}
+	doutc(cl, "ret %d\n", ret);
+	return ret;
+}
+
+/**
+ * ceph_fscrypt_encrypt_pages - encrypt an array of pages
+ * @inode: pointer to inode associated with these pages
+ * @page: pointer to page array
+ * @off: offset into the file that the data starts
+ * @len: max length to encrypt
+ *
+ * Encrypt an array of cleartext pages and return the amount of
+ * data encrypted. Any data in the page prior to the start of the
+ * first complete block in the read is ignored. Any incomplete
+ * crypto blocks at the end of the array are ignored.
+ *
+ * Returns the length of the encrypted data or a negative errno.
+ */
+int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
+				int len)
+{
+	int i, num_blocks;
+	u64 baseblk = off >> CEPH_FSCRYPT_BLOCK_SHIFT;
+	int ret = 0;
+
+	/*
+	 * We can't deal with partial blocks on an encrypted file, so mask off
+	 * the last bit.
+	 */
+	num_blocks = ceph_fscrypt_blocks(off, len & CEPH_FSCRYPT_BLOCK_MASK);
+
+	/* Encrypt each block */
+	for (i = 0; i < num_blocks; ++i) {
+		int blkoff = i << CEPH_FSCRYPT_BLOCK_SHIFT;
+		int pgidx = blkoff >> PAGE_SHIFT;
+		unsigned int pgoffs = offset_in_page(blkoff);
+		int fret;
+
+		fret = ceph_fscrypt_encrypt_block_inplace(inode, page[pgidx],
+				CEPH_FSCRYPT_BLOCK_SIZE, pgoffs,
+				baseblk + i);
+		if (fret < 0) {
+			if (ret == 0)
+				ret = fret;
+			break;
+		}
+		ret += CEPH_FSCRYPT_BLOCK_SIZE;
+	}
+	return ret;
+}

linux-7.2.3/fs/ceph/crypto.h

@@ -0,0 +1,272 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ceph fscrypt functionality
+ */
+
+#ifndef _CEPH_CRYPTO_H
+#define _CEPH_CRYPTO_H
+
+#include <crypto/sha2.h>
+#include <linux/fscrypt.h>
+#include <linux/base64.h>
+
+#define CEPH_FSCRYPT_BLOCK_SHIFT   12
+#define CEPH_FSCRYPT_BLOCK_SIZE    (_AC(1, UL) << CEPH_FSCRYPT_BLOCK_SHIFT)
+#define CEPH_FSCRYPT_BLOCK_MASK	   (~(CEPH_FSCRYPT_BLOCK_SIZE-1))
+
+struct ceph_fs_client;
+struct ceph_acl_sec_ctx;
+struct ceph_mds_request;
+
+struct ceph_fname {
+	struct inode	*dir;
+	char		*name;		// b64 encoded, possibly hashed
+	unsigned char	*ctext;		// binary crypttext (if any)
+	u32		name_len;	// length of name buffer
+	u32		ctext_len;	// length of crypttext
+	bool		no_copy;
+};
+
+/*
+ * Header for the encrypted file when truncating the size, this
+ * will be sent to MDS, and the MDS will update the encrypted
+ * last block and then truncate the size.
+ */
+struct ceph_fscrypt_truncate_size_header {
+	__u8  ver;
+	__u8  compat;
+
+	/*
+	 * It will be sizeof(assert_ver + file_offset + block_size)
+	 * if the last block is empty when it's located in a file
+	 * hole. Or the data_len will plus CEPH_FSCRYPT_BLOCK_SIZE.
+	 */
+	__le32 data_len;
+
+	__le64 change_attr;
+	__le64 file_offset;
+	__le32 block_size;
+} __packed;
+
+struct ceph_fscrypt_auth {
+	__le32	cfa_version;
+	__le32	cfa_blob_len;
+	u8	cfa_blob[FSCRYPT_SET_CONTEXT_MAX_SIZE];
+} __packed;
+
+#define CEPH_FSCRYPT_AUTH_VERSION	1
+static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
+{
+	u32 ctxsize = le32_to_cpu(fa->cfa_blob_len);
+
+	return offsetof(struct ceph_fscrypt_auth, cfa_blob) + ctxsize;
+}
+
+#ifdef CONFIG_FS_ENCRYPTION
+/*
+ * We want to encrypt filenames when creating them, but the encrypted
+ * versions of those names may have illegal characters in them. To mitigate
+ * that, we base64 encode them, but that gives us a result that can exceed
+ * NAME_MAX.
+ *
+ * Follow a similar scheme to fscrypt itself, and cap the filename to a
+ * smaller size. If the ciphertext name is longer than the value below, then
+ * sha256 hash the remaining bytes.
+ *
+ * For the fscrypt_nokey_name struct the dirhash[2] member is useless in ceph
+ * so the corresponding struct will be:
+ *
+ * struct fscrypt_ceph_nokey_name {
+ *	u8 bytes[157];
+ *	u8 sha256[SHA256_DIGEST_SIZE];
+ * }; // 180 bytes => 240 bytes base64-encoded, which is <= NAME_MAX (255)
+ *
+ * (240 bytes is the maximum size allowed for snapshot names to take into
+ *  account the format: '_<SNAPSHOT-NAME>_<INODE-NUMBER>'.)
+ *
+ * Note that for long names that end up having their tail portion hashed, we
+ * must also store the full encrypted name (in the dentry's alternate_name
+ * field).
+ */
+#define CEPH_NOHASH_NAME_MAX (180 - SHA256_DIGEST_SIZE)
+
+void ceph_fscrypt_set_ops(struct super_block *sb);
+
+void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
+
+int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
+				 struct ceph_acl_sec_ctx *as);
+void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+				struct ceph_acl_sec_ctx *as);
+int ceph_encode_encrypted_dname(struct inode *parent, char *buf, int len);
+
+static inline int ceph_fname_alloc_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+	if (!IS_ENCRYPTED(parent))
+		return 0;
+	return fscrypt_fname_alloc_buffer(NAME_MAX, fname);
+}
+
+static inline void ceph_fname_free_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+	if (IS_ENCRYPTED(parent))
+		fscrypt_fname_free_buffer(fname);
+}
+
+int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
+		      struct fscrypt_str *oname, bool *is_nokey);
+int ceph_fscrypt_prepare_readdir(struct inode *dir);
+
+static inline unsigned int ceph_fscrypt_blocks(u64 off, u64 len)
+{
+	/* crypto blocks cannot span more than one page */
+	BUILD_BUG_ON(CEPH_FSCRYPT_BLOCK_SHIFT > PAGE_SHIFT);
+
+	return ((off+len+CEPH_FSCRYPT_BLOCK_SIZE-1) >> CEPH_FSCRYPT_BLOCK_SHIFT) -
+		(off >> CEPH_FSCRYPT_BLOCK_SHIFT);
+}
+
+/*
+ * If we have an encrypted inode then we must adjust the offset and
+ * range of the on-the-wire read to cover an entire encryption block.
+ * The copy will be done using the original offset and length, after
+ * we've decrypted the result.
+ */
+static inline void ceph_fscrypt_adjust_off_and_len(struct inode *inode,
+						   u64 *off, u64 *len)
+{
+	if (IS_ENCRYPTED(inode)) {
+		*len = ceph_fscrypt_blocks(*off, *len) * CEPH_FSCRYPT_BLOCK_SIZE;
+		*off &= CEPH_FSCRYPT_BLOCK_MASK;
+	}
+}
+
+int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num);
+int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+				  struct page *page, unsigned int len,
+				  unsigned int offs, u64 lblk_num);
+int ceph_fscrypt_decrypt_pages(struct inode *inode, struct page **page,
+			       u64 off, int len);
+int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
+				 u64 off, struct ceph_sparse_extent *map,
+				 u32 ext_cnt);
+int ceph_fscrypt_encrypt_pages(struct inode *inode, struct page **page, u64 off,
+			       int len);
+
+static inline struct page *ceph_fscrypt_pagecache_page(struct page *page)
+{
+	return fscrypt_is_bounce_page(page) ? fscrypt_pagecache_page(page) : page;
+}
+
+#else /* CONFIG_FS_ENCRYPTION */
+
+static inline void ceph_fscrypt_set_ops(struct super_block *sb)
+{
+}
+
+static inline void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc)
+{
+}
+
+static inline int ceph_fscrypt_prepare_context(struct inode *dir,
+					       struct inode *inode,
+					       struct ceph_acl_sec_ctx *as)
+{
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static inline void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
+						struct ceph_acl_sec_ctx *as_ctx)
+{
+}
+
+static inline int ceph_encode_encrypted_dname(struct inode *parent, char *buf,
+					      int len)
+{
+	return len;
+}
+
+static inline int ceph_fname_alloc_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+	return 0;
+}
+
+static inline void ceph_fname_free_buffer(struct inode *parent,
+					  struct fscrypt_str *fname)
+{
+}
+
+static inline int ceph_fname_to_usr(const struct ceph_fname *fname,
+				    struct fscrypt_str *tname,
+				    struct fscrypt_str *oname, bool *is_nokey)
+{
+	oname->name = fname->name;
+	oname->len = fname->name_len;
+	return 0;
+}
+
+static inline int ceph_fscrypt_prepare_readdir(struct inode *dir)
+{
+	return 0;
+}
+
+static inline void ceph_fscrypt_adjust_off_and_len(struct inode *inode,
+						   u64 *off, u64 *len)
+{
+}
+
+static inline int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
+					  struct page *page, unsigned int len,
+					  unsigned int offs, u64 lblk_num)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
+					  struct page *page, unsigned int len,
+					  unsigned int offs, u64 lblk_num)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_decrypt_pages(struct inode *inode,
+					     struct page **page, u64 off,
+					     int len)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_decrypt_extents(struct inode *inode,
+					       struct page **page, u64 off,
+					       struct ceph_sparse_extent *map,
+					       u32 ext_cnt)
+{
+	return 0;
+}
+
+static inline int ceph_fscrypt_encrypt_pages(struct inode *inode,
+					     struct page **page, u64 off,
+					     int len)
+{
+	return 0;
+}
+
+static inline struct page *ceph_fscrypt_pagecache_page(struct page *page)
+{
+	return page;
+}
+#endif /* CONFIG_FS_ENCRYPTION */
+
+static inline loff_t ceph_fscrypt_page_offset(struct page *page)
+{
+	return page_offset(ceph_fscrypt_pagecache_page(page));
+}
+
+#endif /* _CEPH_CRYPTO_H */

linux-7.2.3/fs/ceph/debugfs.c

@@ -0,0 +1,745 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/math64.h>
+#include <linux/ktime.h>
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+#include <linux/ceph/decode.h>
+
+#include "super.h"
+
+#ifdef CONFIG_DEBUG_FS
+
+#include "mds_client.h"
+#include "metric.h"
+#include "subvolume_metrics.h"
+
+/**
+ * struct ceph_session_feature_desc - Maps feature bits to names for debugfs
+ * @bit: Feature bit number from enum ceph_feature_type (see mds_client.h)
+ * @name: Human-readable feature name for debugfs output
+ *
+ * Used by metric_features_show() to display negotiated session features.
+ */
+struct ceph_session_feature_desc {
+	unsigned int bit;
+	const char *name;
+};
+
+static const struct ceph_session_feature_desc ceph_session_feature_table[] = {
+	{ CEPHFS_FEATURE_METRIC_COLLECT, "METRIC_COLLECT" },
+	{ CEPHFS_FEATURE_REPLY_ENCODING, "REPLY_ENCODING" },
+	{ CEPHFS_FEATURE_RECLAIM_CLIENT, "RECLAIM_CLIENT" },
+	{ CEPHFS_FEATURE_LAZY_CAP_WANTED, "LAZY_CAP_WANTED" },
+	{ CEPHFS_FEATURE_MULTI_RECONNECT, "MULTI_RECONNECT" },
+	{ CEPHFS_FEATURE_DELEG_INO, "DELEG_INO" },
+	{ CEPHFS_FEATURE_ALTERNATE_NAME, "ALTERNATE_NAME" },
+	{ CEPHFS_FEATURE_NOTIFY_SESSION_STATE, "NOTIFY_SESSION_STATE" },
+	{ CEPHFS_FEATURE_OP_GETVXATTR, "OP_GETVXATTR" },
+	{ CEPHFS_FEATURE_32BITS_RETRY_FWD, "32BITS_RETRY_FWD" },
+	{ CEPHFS_FEATURE_NEW_SNAPREALM_INFO, "NEW_SNAPREALM_INFO" },
+	{ CEPHFS_FEATURE_HAS_OWNER_UIDGID, "HAS_OWNER_UIDGID" },
+	{ CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, "MDS_AUTH_CAPS_CHECK" },
+	{ CEPHFS_FEATURE_SUBVOLUME_METRICS, "SUBVOLUME_METRICS" },
+};
+
+static int mdsmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mdsmap *mdsmap;
+
+	if (!fsc->mdsc || !fsc->mdsc->mdsmap)
+		return 0;
+	mdsmap = fsc->mdsc->mdsmap;
+	seq_printf(s, "epoch %d\n", mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", mdsmap->m_root);
+	seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds);
+	seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout);
+	seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose);
+	for (i = 0; i < mdsmap->possible_max_rank; i++) {
+		struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr;
+		int state = mdsmap->m_info[i].state;
+		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
+			       ceph_pr_addr(addr),
+			       ceph_mds_state_name(state));
+	}
+	return 0;
+}
+
+/*
+ * mdsc debugfs
+ */
+static int mdsc_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_mds_request *req;
+	struct rb_node *rp;
+	char *path;
+
+	mutex_lock(&mdsc->mutex);
+	for (rp = rb_first(&mdsc->request_tree); rp; rp = rb_next(rp)) {
+		req = rb_entry(rp, struct ceph_mds_request, r_node);
+
+		if (req->r_request && req->r_session)
+			seq_printf(s, "%lld\tmds%d\t", req->r_tid,
+				   req->r_session->s_mds);
+		else if (!req->r_request)
+			seq_printf(s, "%lld\t(no request)\t", req->r_tid);
+		else
+			seq_printf(s, "%lld\t(no session)\t", req->r_tid);
+
+		seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
+
+		if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
+			seq_puts(s, "\t(unsafe)");
+		else
+			seq_puts(s, "\t");
+
+		if (req->r_inode) {
+			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
+		} else if (req->r_dentry) {
+			struct ceph_path_info path_info = {0};
+			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
+			if (IS_ERR(path))
+				path = NULL;
+			spin_lock(&req->r_dentry->d_lock);
+			seq_printf(s, " #%llx/%pd (%s)",
+				   ceph_ino(d_inode(req->r_dentry->d_parent)),
+				   req->r_dentry,
+				   path ? path : "");
+			spin_unlock(&req->r_dentry->d_lock);
+			ceph_mdsc_free_path_info(&path_info);
+		} else if (req->r_path1) {
+			seq_printf(s, " #%llx/%s", req->r_ino1.ino,
+				   req->r_path1);
+		} else {
+			seq_printf(s, " #%llx", req->r_ino1.ino);
+		}
+
+		if (req->r_old_dentry) {
+			struct ceph_path_info path_info = {0};
+			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0);
+			if (IS_ERR(path))
+				path = NULL;
+			spin_lock(&req->r_old_dentry->d_lock);
+			seq_printf(s, " #%llx/%pd (%s)",
+				   req->r_old_dentry_dir ?
+				   ceph_ino(req->r_old_dentry_dir) : 0,
+				   req->r_old_dentry,
+				   path ? path : "");
+			spin_unlock(&req->r_old_dentry->d_lock);
+			ceph_mdsc_free_path_info(&path_info);
+		} else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) {
+			if (req->r_ino2.ino)
+				seq_printf(s, " #%llx/%s", req->r_ino2.ino,
+					   req->r_path2);
+			else
+				seq_printf(s, " %s", req->r_path2);
+		}
+
+		seq_puts(s, "\n");
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	return 0;
+}
+
+#define CEPH_LAT_METRIC_SHOW(name, total, avg, min, max, sq) {		\
+	s64 _total, _avg, _min, _max, _sq, _st;				\
+	_avg = ktime_to_us(avg);					\
+	_min = ktime_to_us(min == KTIME_MAX ? 0 : min);			\
+	_max = ktime_to_us(max);					\
+	_total = total - 1;						\
+	_sq = _total > 0 ? DIV64_U64_ROUND_CLOSEST(sq, _total) : 0;	\
+	_st = int_sqrt64(_sq);						\
+	_st = ktime_to_us(_st);						\
+	seq_printf(s, "%-14s%-12lld%-16lld%-16lld%-16lld%lld\n",	\
+		   name, total, _avg, _min, _max, _st);			\
+}
+
+#define CEPH_SZ_METRIC_SHOW(name, total, avg, min, max, sum) {		\
+	u64 _min = min == U64_MAX ? 0 : min;				\
+	seq_printf(s, "%-14s%-12lld%-16llu%-16llu%-16llu%llu\n",	\
+		   name, total, avg, _min, max, sum);			\
+}
+
+static int metrics_file_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *m = &fsc->mdsc->metric;
+
+	seq_printf(s, "item                               total\n");
+	seq_printf(s, "------------------------------------------\n");
+	seq_printf(s, "%-35s%lld\n", "total inodes",
+		   percpu_counter_sum(&m->total_inodes));
+	seq_printf(s, "%-35s%lld\n", "opened files",
+		   atomic64_read(&m->opened_files));
+	seq_printf(s, "%-35s%lld\n", "pinned i_caps",
+		   atomic64_read(&m->total_caps));
+	seq_printf(s, "%-35s%lld\n", "opened inodes",
+		   percpu_counter_sum(&m->opened_inodes));
+	return 0;
+}
+
+static const char * const metric_str[] = {
+	"read",
+	"write",
+	"metadata",
+	"copyfrom"
+};
+static int metrics_latency_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *cm = &fsc->mdsc->metric;
+	struct ceph_metric *m;
+	s64 total, avg, min, max, sq;
+	int i;
+
+	seq_printf(s, "item          total       avg_lat(us)     min_lat(us)     max_lat(us)     stdev(us)\n");
+	seq_printf(s, "-----------------------------------------------------------------------------------\n");
+
+	for (i = 0; i < METRIC_MAX; i++) {
+		m = &cm->metric[i];
+		spin_lock(&m->lock);
+		total = m->total;
+		avg = m->latency_avg;
+		min = m->latency_min;
+		max = m->latency_max;
+		sq = m->latency_sq_sum;
+		spin_unlock(&m->lock);
+		CEPH_LAT_METRIC_SHOW(metric_str[i], total, avg, min, max, sq);
+	}
+
+	return 0;
+}
+
+static int metrics_size_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *cm = &fsc->mdsc->metric;
+	struct ceph_metric *m;
+	s64 total;
+	u64 sum, avg, min, max;
+	int i;
+
+	seq_printf(s, "item          total       avg_sz(bytes)   min_sz(bytes)   max_sz(bytes)  total_sz(bytes)\n");
+	seq_printf(s, "----------------------------------------------------------------------------------------\n");
+
+	for (i = 0; i < METRIC_MAX; i++) {
+		/* skip 'metadata' as it doesn't use the size metric */
+		if (i == METRIC_METADATA)
+			continue;
+		m = &cm->metric[i];
+		spin_lock(&m->lock);
+		total = m->total;
+		sum = m->size_sum;
+		avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
+		min = m->size_min;
+		max = m->size_max;
+		spin_unlock(&m->lock);
+		CEPH_SZ_METRIC_SHOW(metric_str[i], total, avg, min, max, sum);
+	}
+
+	return 0;
+}
+
+static int metrics_caps_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *m = &fsc->mdsc->metric;
+	int nr_caps = 0;
+
+	seq_printf(s, "item          total           miss            hit\n");
+	seq_printf(s, "-------------------------------------------------\n");
+
+	seq_printf(s, "%-14s%-16lld%-16lld%lld\n", "d_lease",
+		   atomic64_read(&m->total_dentries),
+		   percpu_counter_sum(&m->d_lease_mis),
+		   percpu_counter_sum(&m->d_lease_hit));
+
+	nr_caps = atomic64_read(&m->total_caps);
+	seq_printf(s, "%-14s%-16d%-16lld%lld\n", "caps", nr_caps,
+		   percpu_counter_sum(&m->i_caps_mis),
+		   percpu_counter_sum(&m->i_caps_hit));
+
+	return 0;
+}
+
+static int caps_show_cb(struct inode *inode, int mds, void *p)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct seq_file *s = p;
+	struct ceph_cap *cap;
+
+	spin_lock(&ci->i_ceph_lock);
+	cap = __get_cap_for_mds(ci, mds);
+	if (cap)
+		seq_printf(s, "0x%-17llx%-3d%-17s%-17s\n", ceph_ino(inode),
+			   cap->session->s_mds,
+			   ceph_cap_string(cap->issued),
+			   ceph_cap_string(cap->implemented));
+	spin_unlock(&ci->i_ceph_lock);
+	return 0;
+}
+
+static int caps_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	int total, avail, used, reserved, min, i;
+	struct cap_wait	*cw;
+
+	ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min);
+	seq_printf(s, "total\t\t%d\n"
+		   "avail\t\t%d\n"
+		   "used\t\t%d\n"
+		   "reserved\t%d\n"
+		   "min\t\t%d\n\n",
+		   total, avail, used, reserved, min);
+	seq_printf(s, "ino              mds  issued           implemented\n");
+	seq_printf(s, "--------------------------------------------------\n");
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		struct ceph_mds_session *session;
+
+		session = __ceph_lookup_mds_session(mdsc, i);
+		if (!session)
+			continue;
+		mutex_unlock(&mdsc->mutex);
+		mutex_lock(&session->s_mutex);
+		ceph_iterate_session_caps(session, caps_show_cb, s);
+		mutex_unlock(&session->s_mutex);
+		ceph_put_mds_session(session);
+		mutex_lock(&mdsc->mutex);
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	seq_printf(s, "\n\nWaiters:\n--------\n");
+	seq_printf(s, "tgid         ino                need             want\n");
+	seq_printf(s, "-----------------------------------------------------\n");
+
+	spin_lock(&mdsc->caps_list_lock);
+	list_for_each_entry(cw, &mdsc->cap_wait_list, list) {
+		seq_printf(s, "%-13d0x%-17llx%-17s%-17s\n", cw->tgid, cw->ino,
+				ceph_cap_string(cw->need),
+				ceph_cap_string(cw->want));
+	}
+	spin_unlock(&mdsc->caps_list_lock);
+
+	return 0;
+}
+
+static int mds_sessions_show(struct seq_file *s, void *ptr)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_auth_client *ac = fsc->client->monc.auth;
+	struct ceph_options *opt = fsc->client->options;
+	int mds;
+
+	mutex_lock(&mdsc->mutex);
+
+	/* The 'num' portion of an 'entity name' */
+	seq_printf(s, "global_id %llu\n", ac->global_id);
+
+	/* The -o name mount argument */
+	seq_printf(s, "name \"%s\"\n", opt->name ? opt->name : "");
+
+	/* The list of MDS session rank+state */
+	for (mds = 0; mds < mdsc->max_sessions; mds++) {
+		struct ceph_mds_session *session =
+			__ceph_lookup_mds_session(mdsc, mds);
+		if (!session) {
+			continue;
+		}
+		mutex_unlock(&mdsc->mutex);
+		seq_printf(s, "mds.%d %s\n",
+				session->s_mds,
+				ceph_session_state_name(session->s_state));
+
+		ceph_put_mds_session(session);
+		mutex_lock(&mdsc->mutex);
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	return 0;
+}
+
+static int status_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_entity_inst *inst = &fsc->client->msgr.inst;
+	struct ceph_entity_addr *client_addr = ceph_client_addr(fsc->client);
+
+	seq_printf(s, "instance: %s.%lld %s/%u\n", ENTITY_NAME(inst->name),
+		   ceph_pr_addr(client_addr), le32_to_cpu(client_addr->nonce));
+	seq_printf(s, "blocklisted: %s\n", str_true_false(fsc->blocklisted));
+
+	return 0;
+}
+
+static int reset_status_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_client_reset_state *st;
+	u64 trigger = 0, success = 0, failure = 0;
+	unsigned long last_start = 0, last_finish = 0;
+	int last_errno = 0;
+	enum ceph_client_reset_phase phase = CEPH_CLIENT_RESET_IDLE;
+	bool drain_timed_out = false;
+	int sessions_reset = 0;
+	int blocked_requests = 0;
+	char reason[CEPH_CLIENT_RESET_REASON_LEN];
+
+	if (!mdsc)
+		return 0;
+
+	st = &mdsc->reset_state;
+
+	spin_lock(&st->lock);
+	trigger = st->trigger_count;
+	success = st->success_count;
+	failure = st->failure_count;
+	last_start = st->last_start;
+	last_finish = st->last_finish;
+	last_errno = st->last_errno;
+	phase = st->phase;
+	drain_timed_out = st->drain_timed_out;
+	sessions_reset = st->sessions_reset;
+	strscpy(reason, st->last_reason, sizeof(reason));
+	spin_unlock(&st->lock);
+
+	blocked_requests = atomic_read(&st->blocked_requests);
+
+	seq_printf(s, "phase: %s\n", ceph_reset_phase_name(phase));
+	seq_printf(s, "trigger_count: %llu\n", trigger);
+	seq_printf(s, "success_count: %llu\n", success);
+	seq_printf(s, "failure_count: %llu\n", failure);
+	if (last_start)
+		seq_printf(s, "last_start_ms_ago: %u\n",
+			   jiffies_to_msecs(jiffies - last_start));
+	else
+		seq_puts(s, "last_start_ms_ago: (never)\n");
+	if (last_finish)
+		seq_printf(s, "last_finish_ms_ago: %u\n",
+			   jiffies_to_msecs(jiffies - last_finish));
+	else
+		seq_puts(s, "last_finish_ms_ago: (never)\n");
+	seq_printf(s, "last_errno: %d\n", last_errno);
+	seq_printf(s, "last_reason: %s\n",
+		   reason[0] ? reason : "(none)");
+	seq_printf(s, "drain_timed_out: %s\n",
+		   drain_timed_out ? "yes" : "no");
+	seq_printf(s, "sessions_reset: %d\n", sessions_reset);
+	seq_printf(s, "blocked_requests: %d\n", blocked_requests);
+
+	return 0;
+}
+
+static ssize_t reset_trigger_write(struct file *file, const char __user *buf,
+				   size_t len, loff_t *ppos)
+{
+	struct ceph_fs_client *fsc = file->private_data;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	char reason[CEPH_CLIENT_RESET_REASON_LEN];
+	size_t copy;
+	int ret;
+
+	if (!mdsc)
+		return -ENODEV;
+
+	copy = min_t(size_t, len, sizeof(reason) - 1);
+	if (copy && copy_from_user(reason, buf, copy))
+		return -EFAULT;
+	reason[copy] = '\0';
+	strim(reason);
+
+	ret = ceph_mdsc_schedule_reset(mdsc, reason);
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+static int subvolume_metrics_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_subvol_metric_snapshot *snapshot = NULL;
+	u32 nr = 0;
+	u64 total_sent = 0;
+	u64 nonzero_sends = 0;
+	u32 i;
+
+	if (!mdsc) {
+		seq_puts(s, "mds client unavailable\n");
+		return 0;
+	}
+
+	mutex_lock(&mdsc->subvol_metrics_last_mutex);
+	if (mdsc->subvol_metrics_last && mdsc->subvol_metrics_last_nr) {
+		nr = mdsc->subvol_metrics_last_nr;
+		snapshot = kmemdup_array(mdsc->subvol_metrics_last, nr,
+					 sizeof(*snapshot), GFP_KERNEL);
+		if (!snapshot)
+			nr = 0;
+	}
+	total_sent = mdsc->subvol_metrics_sent;
+	nonzero_sends = mdsc->subvol_metrics_nonzero_sends;
+	mutex_unlock(&mdsc->subvol_metrics_last_mutex);
+
+	seq_puts(s, "Last sent subvolume metrics:\n");
+	if (!nr) {
+		seq_puts(s, "  (none)\n");
+	} else {
+		seq_puts(s, "  subvol_id          rd_ops    wr_ops    rd_bytes       wr_bytes       rd_lat_us      wr_lat_us\n");
+		for (i = 0; i < nr; i++) {
+			const struct ceph_subvol_metric_snapshot *e = &snapshot[i];
+
+			seq_printf(s, "  %-18llu %-9llu %-9llu %-14llu %-14llu %-14llu %-14llu\n",
+				   e->subvolume_id,
+				   e->read_ops, e->write_ops,
+				   e->read_bytes, e->write_bytes,
+				   e->read_latency_us, e->write_latency_us);
+		}
+	}
+	kfree(snapshot);
+
+	seq_puts(s, "\nStatistics:\n");
+	seq_printf(s, "  entries_sent:      %llu\n", total_sent);
+	seq_printf(s, "  non_zero_sends:    %llu\n", nonzero_sends);
+
+	seq_puts(s, "\nPending (unsent) subvolume metrics:\n");
+	ceph_subvolume_metrics_dump(&mdsc->subvol_metrics, s);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mdsmap);
+DEFINE_SHOW_ATTRIBUTE(mdsc);
+DEFINE_SHOW_ATTRIBUTE(caps);
+DEFINE_SHOW_ATTRIBUTE(mds_sessions);
+DEFINE_SHOW_ATTRIBUTE(status);
+DEFINE_SHOW_ATTRIBUTE(reset_status);
+DEFINE_SHOW_ATTRIBUTE(metrics_file);
+DEFINE_SHOW_ATTRIBUTE(metrics_latency);
+DEFINE_SHOW_ATTRIBUTE(metrics_size);
+DEFINE_SHOW_ATTRIBUTE(metrics_caps);
+DEFINE_SHOW_ATTRIBUTE(subvolume_metrics);
+
+static int metric_features_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	unsigned long session_features = 0;
+	bool have_session = false;
+	bool metric_collect = false;
+	bool subvol_support = false;
+	bool metrics_enabled = false;
+	bool subvol_enabled = false;
+	int i;
+
+	if (!mdsc) {
+		seq_puts(s, "mds client unavailable\n");
+		return 0;
+	}
+
+	mutex_lock(&mdsc->mutex);
+	if (mdsc->metric.session) {
+		have_session = true;
+		session_features = mdsc->metric.session->s_features;
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	if (have_session) {
+		metric_collect =
+			test_bit(CEPHFS_FEATURE_METRIC_COLLECT,
+				 &session_features);
+		subvol_support =
+			test_bit(CEPHFS_FEATURE_SUBVOLUME_METRICS,
+				 &session_features);
+	}
+
+	metrics_enabled = !disable_send_metrics && have_session && metric_collect;
+	subvol_enabled = metrics_enabled && subvol_support;
+
+	seq_printf(s,
+		   "metrics_enabled: %s (disable_send_metrics=%d, session=%s, metric_collect=%s)\n",
+		   metrics_enabled ? "yes" : "no",
+		   disable_send_metrics ? 1 : 0,
+		   have_session ? "yes" : "no",
+		   metric_collect ? "yes" : "no");
+	seq_printf(s, "subvolume_metrics_enabled: %s\n",
+		   subvol_enabled ? "yes" : "no");
+	seq_printf(s, "session_feature_bits: 0x%lx\n", session_features);
+
+	if (!have_session) {
+		seq_puts(s, "(no active MDS session for metrics)\n");
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ceph_session_feature_table); i++) {
+		const struct ceph_session_feature_desc *desc =
+			&ceph_session_feature_table[i];
+		bool set = test_bit(desc->bit, &session_features);
+
+		seq_printf(s, "  %-24s : %s\n", desc->name,
+			   set ? "yes" : "no");
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(metric_features);
+
+static const struct file_operations ceph_reset_trigger_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = reset_trigger_write,
+	.llseek = noop_llseek,
+};
+
+/*
+ * debugfs
+ */
+static int congestion_kb_set(void *data, u64 val)
+{
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
+
+	fsc->mount_options->congestion_kb = (int)val;
+	return 0;
+}
+
+static int congestion_kb_get(void *data, u64 *val)
+{
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
+
+	*val = (u64)fsc->mount_options->congestion_kb;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
+			congestion_kb_set, "%llu\n");
+
+
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
+{
+	doutc(fsc->client, "begin\n");
+	debugfs_remove(fsc->debugfs_bdi);
+	debugfs_remove(fsc->debugfs_congestion_kb);
+	debugfs_remove(fsc->debugfs_mdsmap);
+	debugfs_remove(fsc->debugfs_mds_sessions);
+	debugfs_remove(fsc->debugfs_caps);
+	debugfs_remove(fsc->debugfs_status);
+	debugfs_remove(fsc->debugfs_mdsc);
+	debugfs_remove_recursive(fsc->debugfs_reset_dir);
+	debugfs_remove(fsc->debugfs_subvolume_metrics);
+	debugfs_remove_recursive(fsc->debugfs_metrics_dir);
+	doutc(fsc->client, "done\n");
+}
+
+void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
+{
+	char name[NAME_MAX];
+
+	doutc(fsc->client, "begin\n");
+	fsc->debugfs_congestion_kb =
+		debugfs_create_file("writeback_congestion_kb",
+				    0600,
+				    fsc->client->debugfs_dir,
+				    fsc,
+				    &congestion_kb_fops);
+
+	snprintf(name, sizeof(name), "../../bdi/%s",
+		 bdi_dev_name(fsc->sb->s_bdi));
+	fsc->debugfs_bdi =
+		debugfs_create_symlink("bdi",
+				       fsc->client->debugfs_dir,
+				       name);
+
+	fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
+					0400,
+					fsc->client->debugfs_dir,
+					fsc,
+					&mdsmap_fops);
+
+	fsc->debugfs_mds_sessions = debugfs_create_file("mds_sessions",
+					0400,
+					fsc->client->debugfs_dir,
+					fsc,
+					&mds_sessions_fops);
+
+	fsc->debugfs_mdsc = debugfs_create_file("mdsc",
+						0400,
+						fsc->client->debugfs_dir,
+						fsc,
+						&mdsc_fops);
+
+	fsc->debugfs_caps = debugfs_create_file("caps",
+						0400,
+						fsc->client->debugfs_dir,
+						fsc,
+						&caps_fops);
+
+	fsc->debugfs_reset_dir = debugfs_create_dir("reset",
+						    fsc->client->debugfs_dir);
+	debugfs_create_file("trigger", 0200,
+			    fsc->debugfs_reset_dir, fsc,
+			    &ceph_reset_trigger_fops);
+	debugfs_create_file("status", 0400,
+			    fsc->debugfs_reset_dir, fsc,
+			    &reset_status_fops);
+
+	fsc->debugfs_status = debugfs_create_file("status",
+						  0400,
+						  fsc->client->debugfs_dir,
+						  fsc,
+						  &status_fops);
+
+	fsc->debugfs_metrics_dir = debugfs_create_dir("metrics",
+						      fsc->client->debugfs_dir);
+
+	debugfs_create_file("file", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_file_fops);
+	debugfs_create_file("latency", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_latency_fops);
+	debugfs_create_file("size", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_size_fops);
+	debugfs_create_file("caps", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_caps_fops);
+	debugfs_create_file("metric_features", 0400, fsc->debugfs_metrics_dir,
+			    fsc, &metric_features_fops);
+	fsc->debugfs_subvolume_metrics =
+		debugfs_create_file("subvolumes", 0400,
+				    fsc->debugfs_metrics_dir, fsc,
+				    &subvolume_metrics_fops);
+	doutc(fsc->client, "done\n");
+}
+
+
+#else  /* CONFIG_DEBUG_FS */
+
+void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
+{
+}
+
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
+{
+}
+
+#endif  /* CONFIG_DEBUG_FS */

linux-7.2.3/fs/ceph/export.c

@@ -0,0 +1,618 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/exportfs.h>
+#include <linux/slab.h>
+#include <linux/unaligned.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include "crypto.h"
+
+/*
+ * Basic fh
+ */
+struct ceph_nfs_fh {
+	u64 ino;
+} __attribute__ ((packed));
+
+/*
+ * Larger fh that includes parent ino.
+ */
+struct ceph_nfs_confh {
+	u64 ino, parent_ino;
+} __attribute__ ((packed));
+
+/*
+ * fh for snapped inode
+ */
+struct ceph_nfs_snapfh {
+	u64 ino;
+	u64 snapid;
+	u64 parent_ino;
+	u32 hash;
+} __attribute__ ((packed));
+
+#define BYTES_PER_U32		(sizeof(u32))
+#define CEPH_FH_BASIC_SIZE \
+	(sizeof(struct ceph_nfs_fh) / BYTES_PER_U32)
+#define CEPH_FH_WITH_PARENT_SIZE \
+	(sizeof(struct ceph_nfs_confh) / BYTES_PER_U32)
+#define CEPH_FH_SNAPPED_INODE_SIZE \
+	(sizeof(struct ceph_nfs_snapfh) / BYTES_PER_U32)
+
+static int ceph_encode_snapfh(struct inode *inode, u32 *rawfh, int *max_len,
+			      struct inode *parent_inode)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	static const int snap_handle_length = CEPH_FH_SNAPPED_INODE_SIZE;
+	struct ceph_nfs_snapfh *sfh = (void *)rawfh;
+	u64 snapid = ceph_snap(inode);
+	int ret;
+	bool no_parent = true;
+
+	if (*max_len < snap_handle_length) {
+		*max_len = snap_handle_length;
+		ret = FILEID_INVALID;
+		goto out;
+	}
+
+	ret =  -EINVAL;
+	if (snapid != CEPH_SNAPDIR) {
+		struct inode *dir;
+		struct dentry *dentry = d_find_alias(inode);
+		if (!dentry)
+			goto out;
+
+		rcu_read_lock();
+		dir = d_inode_rcu(dentry->d_parent);
+		if (ceph_snap(dir) != CEPH_SNAPDIR) {
+			sfh->parent_ino = ceph_ino(dir);
+			sfh->hash = ceph_dentry_hash(dir, dentry);
+			no_parent = false;
+		}
+		rcu_read_unlock();
+		dput(dentry);
+	}
+
+	if (no_parent) {
+		if (!S_ISDIR(inode->i_mode))
+			goto out;
+		sfh->parent_ino = sfh->ino;
+		sfh->hash = 0;
+	}
+	sfh->ino = ceph_ino(inode);
+	sfh->snapid = snapid;
+
+	*max_len = snap_handle_length;
+	ret = FILEID_BTRFS_WITH_PARENT;
+out:
+	doutc(cl, "%p %llx.%llx ret=%d\n", inode, ceph_vinop(inode), ret);
+	return ret;
+}
+
+static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
+			  struct inode *parent_inode)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	static const int handle_length = CEPH_FH_BASIC_SIZE;
+	static const int connected_handle_length = CEPH_FH_WITH_PARENT_SIZE;
+	int type;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return ceph_encode_snapfh(inode, rawfh, max_len, parent_inode);
+
+	if (parent_inode && (*max_len < connected_handle_length)) {
+		*max_len = connected_handle_length;
+		return FILEID_INVALID;
+	} else if (*max_len < handle_length) {
+		*max_len = handle_length;
+		return FILEID_INVALID;
+	}
+
+	if (parent_inode) {
+		struct ceph_nfs_confh *cfh = (void *)rawfh;
+		doutc(cl, "%p %llx.%llx with parent %p %llx.%llx\n", inode,
+		      ceph_vinop(inode), parent_inode, ceph_vinop(parent_inode));
+		cfh->ino = ceph_ino(inode);
+		cfh->parent_ino = ceph_ino(parent_inode);
+		*max_len = connected_handle_length;
+		type = FILEID_INO32_GEN_PARENT;
+	} else {
+		struct ceph_nfs_fh *fh = (void *)rawfh;
+		doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
+		fh->ino = ceph_ino(inode);
+		*max_len = handle_length;
+		type = FILEID_INO32_GEN;
+	}
+	return type;
+}
+
+static struct inode *__lookup_inode(struct super_block *sb, u64 ino)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(sb)->mdsc;
+	struct inode *inode;
+	struct ceph_vino vino;
+	int err;
+
+	vino.ino = ino;
+	vino.snap = CEPH_NOSNAP;
+
+	if (ceph_vino_is_reserved(vino))
+		return ERR_PTR(-ESTALE);
+
+	inode = ceph_find_inode(sb, vino);
+	if (!inode) {
+		struct ceph_mds_request *req;
+		int mask;
+
+		req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
+					       USE_ANY_MDS);
+		if (IS_ERR(req))
+			return ERR_CAST(req);
+
+		mask = CEPH_STAT_CAP_INODE;
+		if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+			mask |= CEPH_CAP_XATTR_SHARED;
+		req->r_args.lookupino.mask = cpu_to_le32(mask);
+
+		req->r_ino1 = vino;
+		req->r_num_caps = 1;
+		err = ceph_mdsc_do_request(mdsc, NULL, req);
+		inode = req->r_target_inode;
+		if (inode)
+			ihold(inode);
+		ceph_mdsc_put_request(req);
+		if (!inode)
+			return err < 0 ? ERR_PTR(err) : ERR_PTR(-ESTALE);
+	} else {
+		if (ceph_inode_is_shutdown(inode)) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+	}
+	return inode;
+}
+
+struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino)
+{
+	struct inode *inode = __lookup_inode(sb, ino);
+	if (IS_ERR(inode))
+		return inode;
+	if (inode->i_nlink == 0) {
+		iput(inode);
+		return ERR_PTR(-ESTALE);
+	}
+	return inode;
+}
+
+static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
+{
+	struct inode *inode = __lookup_inode(sb, ino);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int err;
+
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	/* We need LINK caps to reliably check i_nlink */
+	err = ceph_do_getattr(inode, CEPH_CAP_LINK_SHARED, false);
+	if (err) {
+		iput(inode);
+		return ERR_PTR(err);
+	}
+	/* -ESTALE if inode as been unlinked and no file is open */
+	if ((inode->i_nlink == 0) && !__ceph_is_file_opened(ci)) {
+		iput(inode);
+		return ERR_PTR(-ESTALE);
+	}
+	return d_obtain_alias(inode);
+}
+
+static struct dentry *__snapfh_to_dentry(struct super_block *sb,
+					  struct ceph_nfs_snapfh *sfh,
+					  bool want_parent)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_mds_request *req;
+	struct inode *inode;
+	struct ceph_vino vino;
+	int mask;
+	int err;
+	bool unlinked = false;
+
+	if (want_parent) {
+		vino.ino = sfh->parent_ino;
+		if (sfh->snapid == CEPH_SNAPDIR)
+			vino.snap = CEPH_NOSNAP;
+		else if (sfh->ino == sfh->parent_ino)
+			vino.snap = CEPH_SNAPDIR;
+		else
+			vino.snap = sfh->snapid;
+	} else {
+		vino.ino = sfh->ino;
+		vino.snap = sfh->snapid;
+	}
+
+	if (ceph_vino_is_reserved(vino))
+		return ERR_PTR(-ESTALE);
+
+	inode = ceph_find_inode(sb, vino);
+	if (inode) {
+		if (ceph_inode_is_shutdown(inode)) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+		return d_obtain_alias(inode);
+	}
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
+				       USE_ANY_MDS);
+	if (IS_ERR(req))
+		return ERR_CAST(req);
+
+	mask = CEPH_STAT_CAP_INODE;
+	if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+		mask |= CEPH_CAP_XATTR_SHARED;
+	req->r_args.lookupino.mask = cpu_to_le32(mask);
+	if (vino.snap < CEPH_NOSNAP) {
+		req->r_args.lookupino.snapid = cpu_to_le64(vino.snap);
+		if (!want_parent && sfh->ino != sfh->parent_ino) {
+			req->r_args.lookupino.parent =
+					cpu_to_le64(sfh->parent_ino);
+			req->r_args.lookupino.hash =
+					cpu_to_le32(sfh->hash);
+		}
+	}
+
+	req->r_ino1 = vino;
+	req->r_num_caps = 1;
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	inode = req->r_target_inode;
+	if (inode) {
+		if (vino.snap == CEPH_SNAPDIR) {
+			if (inode->i_nlink == 0)
+				unlinked = true;
+			inode = ceph_get_snapdir(inode);
+		} else if (ceph_snap(inode) == vino.snap) {
+			ihold(inode);
+		} else {
+			/* mds does not support lookup snapped inode */
+			inode = ERR_PTR(-EOPNOTSUPP);
+		}
+	} else {
+		inode = ERR_PTR(-ESTALE);
+	}
+	ceph_mdsc_put_request(req);
+
+	if (want_parent) {
+		doutc(cl, "%llx.%llx\n err=%d\n", vino.ino, vino.snap, err);
+	} else {
+		doutc(cl, "%llx.%llx parent %llx hash %x err=%d", vino.ino,
+		      vino.snap, sfh->parent_ino, sfh->hash, err);
+	}
+	/* see comments in ceph_get_parent() */
+	return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode);
+}
+
+/*
+ * convert regular fh to dentry
+ */
+static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
+					struct fid *fid,
+					int fh_len, int fh_type)
+{
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
+	struct ceph_nfs_fh *fh = (void *)fid->raw;
+
+	if (fh_type == FILEID_BTRFS_WITH_PARENT) {
+		struct ceph_nfs_snapfh *sfh = (void *)fid->raw;
+		return __snapfh_to_dentry(sb, sfh, false);
+	}
+
+	if (fh_type != FILEID_INO32_GEN  &&
+	    fh_type != FILEID_INO32_GEN_PARENT)
+		return NULL;
+	if (fh_len < sizeof(*fh) / BYTES_PER_U32)
+		return NULL;
+
+	doutc(fsc->client, "%llx\n", fh->ino);
+	return __fh_to_dentry(sb, fh->ino);
+}
+
+static struct dentry *__get_parent(struct super_block *sb,
+				   struct dentry *child, u64 ino)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(sb)->mdsc;
+	struct ceph_mds_request *req;
+	struct inode *inode;
+	int mask;
+	int err;
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
+				       USE_ANY_MDS);
+	if (IS_ERR(req))
+		return ERR_CAST(req);
+
+	if (child) {
+		req->r_inode = d_inode(child);
+		ihold(d_inode(child));
+	} else {
+		req->r_ino1 = (struct ceph_vino) {
+			.ino = ino,
+			.snap = CEPH_NOSNAP,
+		};
+	}
+
+	mask = CEPH_STAT_CAP_INODE;
+	if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+		mask |= CEPH_CAP_XATTR_SHARED;
+	req->r_args.getattr.mask = cpu_to_le32(mask);
+
+	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);
+	ceph_mdsc_put_request(req);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	return d_obtain_alias(inode);
+}
+
+static struct dentry *ceph_get_parent(struct dentry *child)
+{
+	struct inode *inode = d_inode(child);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	struct dentry *dn;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP) {
+		struct inode* dir;
+		bool unlinked = false;
+		/* do not support non-directory */
+		if (!d_is_dir(child)) {
+			dn = ERR_PTR(-EINVAL);
+			goto out;
+		}
+		dir = __lookup_inode(inode->i_sb, ceph_ino(inode));
+		if (IS_ERR(dir)) {
+			dn = ERR_CAST(dir);
+			goto out;
+		}
+		/* There can be multiple paths to access snapped inode.
+		 * For simplicity, treat snapdir of head inode as parent */
+		if (ceph_snap(inode) != CEPH_SNAPDIR) {
+			struct inode *snapdir = ceph_get_snapdir(dir);
+			if (dir->i_nlink == 0)
+				unlinked = true;
+			iput(dir);
+			if (IS_ERR(snapdir)) {
+				dn = ERR_CAST(snapdir);
+				goto out;
+			}
+			dir = snapdir;
+		}
+		/* If directory has already been deleted, further get_parent
+		 * will fail. Do not mark snapdir dentry as disconnected,
+		 * this prevents exportfs from doing further get_parent. */
+		if (unlinked)
+			dn = d_obtain_root(dir);
+		else
+			dn = d_obtain_alias(dir);
+	} else {
+		dn = __get_parent(child->d_sb, child, 0);
+	}
+out:
+	doutc(cl, "child %p %p %llx.%llx err=%ld\n", child, inode,
+	      ceph_vinop(inode), (long)PTR_ERR_OR_ZERO(dn));
+	return dn;
+}
+
+/*
+ * convert regular fh to parent
+ */
+static struct dentry *ceph_fh_to_parent(struct super_block *sb,
+					struct fid *fid,
+					int fh_len, int fh_type)
+{
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
+	struct ceph_nfs_confh *cfh = (void *)fid->raw;
+	struct dentry *dentry;
+
+	if (fh_type == FILEID_BTRFS_WITH_PARENT) {
+		struct ceph_nfs_snapfh *sfh = (void *)fid->raw;
+		return __snapfh_to_dentry(sb, sfh, true);
+	}
+
+	if (fh_type != FILEID_INO32_GEN_PARENT)
+		return NULL;
+	if (fh_len < sizeof(*cfh) / BYTES_PER_U32)
+		return NULL;
+
+	doutc(fsc->client, "%llx\n", cfh->parent_ino);
+	dentry = __get_parent(sb, NULL, cfh->ino);
+	if (unlikely(dentry == ERR_PTR(-ENOENT)))
+		dentry = __fh_to_dentry(sb, cfh->parent_ino);
+	return dentry;
+}
+
+static int __get_snap_name(struct dentry *parent, char *name,
+			   struct dentry *child)
+{
+	struct inode *inode = d_inode(child);
+	struct inode *dir = d_inode(parent);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_mds_request *req = NULL;
+	char *last_name = NULL;
+	unsigned next_offset = 2;
+	int err = -EINVAL;
+
+	if (ceph_ino(inode) != ceph_ino(dir))
+		goto out;
+	if (ceph_snap(inode) == CEPH_SNAPDIR) {
+		if (ceph_snap(dir) == CEPH_NOSNAP) {
+			/*
+			 * .get_name() from struct export_operations
+			 * assumes that its 'name' parameter is pointing
+			 * to a NAME_MAX+1 sized buffer
+			 */
+			strscpy(name, fsc->mount_options->snapdir_name,
+				NAME_MAX + 1);
+			err = 0;
+		}
+		goto out;
+	}
+	if (ceph_snap(dir) != CEPH_SNAPDIR)
+		goto out;
+
+	while (1) {
+		struct ceph_mds_reply_info_parsed *rinfo;
+		struct ceph_mds_reply_dir_entry *rde;
+		int i;
+
+		req = ceph_mdsc_create_request(fsc->mdsc, CEPH_MDS_OP_LSSNAP,
+					       USE_AUTH_MDS);
+		if (IS_ERR(req)) {
+			err = PTR_ERR(req);
+			req = NULL;
+			goto out;
+		}
+		err = ceph_alloc_readdir_reply_buffer(req, inode);
+		if (err)
+			goto out;
+
+		req->r_direct_mode = USE_AUTH_MDS;
+		req->r_readdir_offset = next_offset;
+		req->r_args.readdir.flags =
+				cpu_to_le16(CEPH_READDIR_REPLY_BITFLAGS);
+		if (last_name) {
+			req->r_path2 = last_name;
+			last_name = NULL;
+		}
+
+		req->r_inode = dir;
+		ihold(dir);
+		req->r_dentry = dget(parent);
+
+		inode_lock(dir);
+		err = ceph_mdsc_do_request(fsc->mdsc, NULL, req);
+		inode_unlock(dir);
+
+		if (err < 0)
+			goto out;
+
+		rinfo = &req->r_reply_info;
+		for (i = 0; i < rinfo->dir_nr; i++) {
+			rde = rinfo->dir_entries + i;
+			BUG_ON(!rde->inode.in);
+			if (ceph_snap(inode) ==
+			    le64_to_cpu(rde->inode.in->snapid)) {
+				memcpy(name, rde->name, rde->name_len);
+				name[rde->name_len] = '\0';
+				err = 0;
+				goto out;
+			}
+		}
+
+		if (rinfo->dir_end)
+			break;
+
+		BUG_ON(rinfo->dir_nr <= 0);
+		rde = rinfo->dir_entries + (rinfo->dir_nr - 1);
+		next_offset += rinfo->dir_nr;
+		last_name = kstrndup(rde->name, rde->name_len, GFP_KERNEL);
+		if (!last_name) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		ceph_mdsc_put_request(req);
+		req = NULL;
+	}
+	err = -ENOENT;
+out:
+	if (req)
+		ceph_mdsc_put_request(req);
+	kfree(last_name);
+	doutc(fsc->client, "child dentry %p %p %llx.%llx err=%d\n", child,
+	      inode, ceph_vinop(inode), err);
+	return err;
+}
+
+static int ceph_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct ceph_mds_client *mdsc;
+	struct ceph_mds_request *req;
+	struct inode *dir = d_inode(parent);
+	struct inode *inode = d_inode(child);
+	struct ceph_mds_reply_info_parsed *rinfo;
+	int err;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return __get_snap_name(parent, name, child);
+
+	mdsc = ceph_inode_to_fs_client(inode)->mdsc;
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
+				       USE_ANY_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	inode_lock(dir);
+	req->r_inode = inode;
+	ihold(inode);
+	req->r_ino2 = ceph_vino(d_inode(parent));
+	req->r_parent = dir;
+	ihold(dir);
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
+	req->r_num_caps = 2;
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	inode_unlock(dir);
+
+	if (err)
+		goto out;
+
+	rinfo = &req->r_reply_info;
+	if (!IS_ENCRYPTED(dir)) {
+		memcpy(name, rinfo->dname, rinfo->dname_len);
+		name[rinfo->dname_len] = 0;
+	} else {
+		struct fscrypt_str oname = FSTR_INIT(NULL, 0);
+		struct ceph_fname fname = { .dir	= dir,
+					    .name	= rinfo->dname,
+					    .ctext	= rinfo->altname,
+					    .name_len	= rinfo->dname_len,
+					    .ctext_len	= rinfo->altname_len };
+
+		err = ceph_fname_alloc_buffer(dir, &oname);
+		if (err < 0)
+			goto out;
+
+		err = ceph_fname_to_usr(&fname, NULL, &oname, NULL);
+		if (!err) {
+			memcpy(name, oname.name, oname.len);
+			name[oname.len] = 0;
+		}
+		ceph_fname_free_buffer(dir, &oname);
+	}
+out:
+	doutc(mdsc->fsc->client, "child dentry %p %p %llx.%llx err %d %s%s\n",
+	      child, inode, ceph_vinop(inode), err, err ? "" : "name ",
+	      err ? "" : name);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+const struct export_operations ceph_export_ops = {
+	.encode_fh = ceph_encode_fh,
+	.fh_to_dentry = ceph_fh_to_dentry,
+	.fh_to_parent = ceph_fh_to_parent,
+	.get_parent = ceph_get_parent,
+	.get_name = ceph_get_name,
+};

linux-7.2.3/fs/ceph/io.c

@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016 Trond Myklebust
+ * Copyright (c) 2019 Jeff Layton
+ *
+ * I/O and data path helper functionality.
+ *
+ * Heavily borrowed from equivalent code in fs/nfs/io.c
+ */
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/rwsem.h>
+#include <linux/fs.h>
+
+#include "super.h"
+#include "io.h"
+
+/* Call with exclusively locked inode->i_rwsem */
+static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
+{
+	bool is_odirect;
+
+	lockdep_assert_held_write(&inode->i_rwsem);
+
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	if (is_odirect) {
+		clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+		/* ensure modified bit is visible */
+		smp_mb__after_atomic();
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (is_odirect)
+		inode_dio_wait(inode);
+}
+
+/**
+ * ceph_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the CEPH_I_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * CEPH_I_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int ceph_start_io_read(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_odirect;
+	int err;
+
+	/* Be an optimist! */
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	spin_unlock(&ci->i_ceph_lock);
+	if (!is_odirect)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
+	ceph_block_o_direct(ci, inode);
+	downgrade_write(&inode->i_rwsem);
+
+	return 0;
+}
+
+/**
+ * ceph_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+ceph_end_io_read(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}
+
+/**
+ * ceph_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int ceph_start_io_write(struct inode *inode)
+{
+	int err = down_write_killable(&inode->i_rwsem);
+	if (!err)
+		ceph_block_o_direct(ceph_inode(inode), inode);
+	return err;
+}
+
+/**
+ * ceph_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void
+ceph_end_io_write(struct inode *inode)
+{
+	up_write(&inode->i_rwsem);
+}
+
+/* Call with exclusively locked inode->i_rwsem */
+static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
+{
+	bool is_odirect;
+
+	lockdep_assert_held_write(&inode->i_rwsem);
+
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	if (!is_odirect) {
+		set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+		/* ensure modified bit is visible */
+		smp_mb__after_atomic();
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (!is_odirect) {
+		/* FIXME: unmap_mapping_range? */
+		filemap_write_and_wait(inode->i_mapping);
+	}
+}
+
+/**
+ * ceph_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the CEPH_I_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * CEPH_I_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int ceph_start_io_direct(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_odirect;
+	int err;
+
+	/* Be an optimist! */
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
+	spin_lock(&ci->i_ceph_lock);
+	/* ensure that bit state is consistent */
+	smp_mb__before_atomic();
+	is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+	spin_unlock(&ci->i_ceph_lock);
+	if (is_odirect)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+
+	ceph_block_buffered(ci, inode);
+	downgrade_write(&inode->i_rwsem);
+
+	return 0;
+}
+
+/**
+ * ceph_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+ceph_end_io_direct(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}

linux-7.2.3/fs/ceph/io.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_IO_H
+#define _FS_CEPH_IO_H
+
+#include <linux/compiler_attributes.h>
+
+int __must_check ceph_start_io_read(struct inode *inode);
+void ceph_end_io_read(struct inode *inode);
+int __must_check ceph_start_io_write(struct inode *inode);
+void ceph_end_io_write(struct inode *inode);
+int __must_check ceph_start_io_direct(struct inode *inode);
+void ceph_end_io_direct(struct inode *inode);
+
+#endif /* FS_CEPH_IO_H */

linux-7.2.3/fs/ceph/ioctl.c

@@ -0,0 +1,438 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+#include <linux/in.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include "ioctl.h"
+#include <linux/ceph/striper.h>
+#include <linux/fscrypt.h>
+
+/*
+ * ioctls
+ */
+
+/*
+ * get and set the file layout
+ */
+static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
+{
+	struct ceph_inode_info *ci = ceph_inode(file_inode(file));
+	struct ceph_ioctl_layout l;
+	int err;
+
+	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
+	if (!err) {
+		l.stripe_unit = ci->i_layout.stripe_unit;
+		l.stripe_count = ci->i_layout.stripe_count;
+		l.object_size = ci->i_layout.object_size;
+		l.data_pool = ci->i_layout.pool_id;
+		l.preferred_osd = -1;
+		if (copy_to_user(arg, &l, sizeof(l)))
+			return -EFAULT;
+	}
+
+	return err;
+}
+
+static long __validate_layout(struct ceph_mds_client *mdsc,
+			      struct ceph_ioctl_layout *l)
+{
+	int i, err;
+
+	/* validate striping parameters */
+	if ((l->object_size & ~PAGE_MASK) ||
+	    (l->stripe_unit & ~PAGE_MASK) ||
+	    ((unsigned)l->stripe_unit != 0 &&
+	     ((unsigned)l->object_size % (unsigned)l->stripe_unit)))
+		return -EINVAL;
+
+	/* make sure it's a valid data pool */
+	mutex_lock(&mdsc->mutex);
+	err = -EINVAL;
+	for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+		if (mdsc->mdsmap->m_data_pg_pools[i] == l->data_pool) {
+			err = 0;
+			break;
+		}
+	mutex_unlock(&mdsc->mutex);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	struct ceph_inode_info *ci = ceph_inode(file_inode(file));
+	struct ceph_ioctl_layout nl;
+	int err;
+
+	if (!inode_owner_or_capable(file_mnt_idmap(file), inode))
+		return -EACCES;
+
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	/* validate changed params against current layout */
+	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
+	if (err)
+		return err;
+
+	memset(&nl, 0, sizeof(nl));
+	if (l.stripe_count)
+		nl.stripe_count = l.stripe_count;
+	else
+		nl.stripe_count = ci->i_layout.stripe_count;
+	if (l.stripe_unit)
+		nl.stripe_unit = l.stripe_unit;
+	else
+		nl.stripe_unit = ci->i_layout.stripe_unit;
+	if (l.object_size)
+		nl.object_size = l.object_size;
+	else
+		nl.object_size = ci->i_layout.object_size;
+	if (l.data_pool)
+		nl.data_pool = l.data_pool;
+	else
+		nl.data_pool = ci->i_layout.pool_id;
+
+	/* this is obsolete, and always -1 */
+	nl.preferred_osd = -1;
+
+	err = __validate_layout(mdsc, &nl);
+	if (err)
+		return err;
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
+				       USE_AUTH_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = inode;
+	ihold(inode);
+	req->r_num_caps = 1;
+
+	req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
+
+	req->r_args.setlayout.layout.fl_stripe_unit =
+		cpu_to_le32(l.stripe_unit);
+	req->r_args.setlayout.layout.fl_stripe_count =
+		cpu_to_le32(l.stripe_count);
+	req->r_args.setlayout.layout.fl_object_size =
+		cpu_to_le32(l.object_size);
+	req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
+
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+/*
+ * Set a layout policy on a directory inode. All items in the tree
+ * rooted at this inode will inherit this layout on creation,
+ * (It doesn't apply retroactively )
+ * unless a subdirectory has its own layout policy.
+ */
+static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	int err;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+
+	if (!inode_owner_or_capable(file_mnt_idmap(file), inode))
+		return -EACCES;
+
+	/* copy and validate */
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	err = __validate_layout(mdsc, &l);
+	if (err)
+		return err;
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
+				       USE_AUTH_MDS);
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = inode;
+	ihold(inode);
+	req->r_num_caps = 1;
+
+	req->r_args.setlayout.layout.fl_stripe_unit =
+			cpu_to_le32(l.stripe_unit);
+	req->r_args.setlayout.layout.fl_stripe_count =
+			cpu_to_le32(l.stripe_count);
+	req->r_args.setlayout.layout.fl_object_size =
+			cpu_to_le32(l.object_size);
+	req->r_args.setlayout.layout.fl_pg_pool =
+			cpu_to_le32(l.data_pool);
+
+	err = ceph_mdsc_do_request(mdsc, inode, req);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+/*
+ * Return object name, size/offset information, and location (OSD
+ * number, network address) for a given file offset.
+ */
+static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
+{
+	struct ceph_ioctl_dataloc dl;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_fs_client(inode->i_sb)->client->osdc;
+	struct ceph_object_locator oloc;
+	CEPH_DEFINE_OID_ONSTACK(oid);
+	u32 xlen;
+	u64 tmp;
+	struct ceph_pg pgid;
+	int r;
+
+	/* copy and validate */
+	if (copy_from_user(&dl, arg, sizeof(dl)))
+		return -EFAULT;
+
+	down_read(&osdc->lock);
+	ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, 1,
+				      &dl.object_no, &dl.object_offset, &xlen);
+	dl.file_offset -= dl.object_offset;
+	dl.object_size = ci->i_layout.object_size;
+	dl.block_size = ci->i_layout.stripe_unit;
+
+	/* block_offset = object_offset % block_size */
+	tmp = dl.object_offset;
+	dl.block_offset = do_div(tmp, dl.block_size);
+
+	snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
+		 ceph_ino(inode), dl.object_no);
+
+	oloc.pool = ci->i_layout.pool_id;
+	oloc.pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
+	ceph_oid_printf(&oid, "%s", dl.object_name);
+
+	r = ceph_object_locator_to_pg(osdc->osdmap, &oid, &oloc, &pgid);
+
+	ceph_oloc_destroy(&oloc);
+	if (r < 0) {
+		up_read(&osdc->lock);
+		return r;
+	}
+
+	dl.osd = ceph_pg_to_acting_primary(osdc->osdmap, &pgid);
+	if (dl.osd >= 0) {
+		struct ceph_entity_addr *a =
+			ceph_osd_addr(osdc->osdmap, dl.osd);
+		if (a)
+			memcpy(&dl.osd_addr, &a->in_addr, sizeof(dl.osd_addr));
+	} else {
+		memset(&dl.osd_addr, 0, sizeof(dl.osd_addr));
+	}
+	up_read(&osdc->lock);
+
+	/* send result back to user */
+	if (copy_to_user(arg, &dl, sizeof(dl)))
+		return -EFAULT;
+
+	return 0;
+}
+
+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_fs_client(inode)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
+	bool is_file_already_lazy = false;
+
+	spin_lock(&ci->i_ceph_lock);
+	if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
+		fi->fmode |= CEPH_FILE_MODE_LAZY;
+		ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
+		__ceph_touch_fmode(ci, mdsc, fi->fmode);
+	} else {
+		is_file_already_lazy = true;
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (is_file_already_lazy) {
+		doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode,
+		      ceph_vinop(inode));
+	} else {
+		doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode,
+		      ceph_vinop(inode));
+
+		ceph_check_caps(ci, 0);
+	}
+
+	return 0;
+}
+
+static long ceph_ioctl_syncio(struct file *file)
+{
+	struct ceph_file_info *fi = file->private_data;
+
+	fi->flags |= CEPH_F_SYNC;
+	return 0;
+}
+
+static int vet_mds_for_fscrypt(struct file *file)
+{
+	int i, ret = -EOPNOTSUPP;
+	struct ceph_mds_client	*mdsc = ceph_sb_to_mdsc(file_inode(file)->i_sb);
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		struct ceph_mds_session *s = mdsc->sessions[i];
+
+		if (!s)
+			continue;
+		if (test_bit(CEPHFS_FEATURE_ALTERNATE_NAME, &s->s_features))
+			ret = 0;
+		break;
+	}
+	mutex_unlock(&mdsc->mutex);
+	return ret;
+}
+
+static long ceph_set_encryption_policy(struct file *file, unsigned long arg)
+{
+	int ret, got = 0;
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	/* encrypted directories can't have striped layout */
+	if (ci->i_layout.stripe_count > 1)
+		return -EINVAL;
+
+	ret = vet_mds_for_fscrypt(file);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ensure we hold these caps so that we _know_ that the rstats check
+	 * in the empty_dir check is reliable.
+	 */
+	ret = ceph_get_caps(file, CEPH_CAP_FILE_SHARED, 0, -1, &got);
+	if (ret)
+		return ret;
+
+	ret = fscrypt_ioctl_set_policy(file, (const void __user *)arg);
+	if (got)
+		ceph_put_cap_refs(ci, got);
+
+	return ret;
+}
+
+static const char *ceph_ioctl_cmd_name(const unsigned int cmd)
+{
+	switch (cmd) {
+	case CEPH_IOC_GET_LAYOUT:
+		return "get_layout";
+	case CEPH_IOC_SET_LAYOUT:
+		return "set_layout";
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return "set_layout_policy";
+	case CEPH_IOC_GET_DATALOC:
+		return "get_dataloc";
+	case CEPH_IOC_LAZYIO:
+		return "lazyio";
+	case CEPH_IOC_SYNCIO:
+		return "syncio";
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+		return "set_encryption_policy";
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		return "get_encryption_policy";
+	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+		return "get_encryption_policy_ex";
+	case FS_IOC_ADD_ENCRYPTION_KEY:
+		return "add_encryption_key";
+	case FS_IOC_REMOVE_ENCRYPTION_KEY:
+		return "remove_encryption_key";
+	case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+		return "remove_encryption_key_all_users";
+	case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+		return "get_encryption_key_status";
+	case FS_IOC_GET_ENCRYPTION_NONCE:
+		return "get_encryption_nonce";
+	default:
+		return "unknown";
+	}
+}
+
+long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	int ret;
+
+	doutc(fsc->client, "file %p %p %llx.%llx cmd %s arg %lu\n", file,
+	      inode, ceph_vinop(inode), ceph_ioctl_cmd_name(cmd), arg);
+	switch (cmd) {
+	case CEPH_IOC_GET_LAYOUT:
+		return ceph_ioctl_get_layout(file, (void __user *)arg);
+
+	case CEPH_IOC_SET_LAYOUT:
+		return ceph_ioctl_set_layout(file, (void __user *)arg);
+
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return ceph_ioctl_set_layout_policy(file, (void __user *)arg);
+
+	case CEPH_IOC_GET_DATALOC:
+		return ceph_ioctl_get_dataloc(file, (void __user *)arg);
+
+	case CEPH_IOC_LAZYIO:
+		return ceph_ioctl_lazyio(file);
+
+	case CEPH_IOC_SYNCIO:
+		return ceph_ioctl_syncio(file);
+
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+		return ceph_set_encryption_policy(file, arg);
+
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_policy(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_policy_ex(file, (void __user *)arg);
+
+	case FS_IOC_ADD_ENCRYPTION_KEY:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_add_key(file, (void __user *)arg);
+
+	case FS_IOC_REMOVE_ENCRYPTION_KEY:
+		return fscrypt_ioctl_remove_key(file, (void __user *)arg);
+
+	case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+		return fscrypt_ioctl_remove_key_all_users(file,
+							  (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+		return fscrypt_ioctl_get_key_status(file, (void __user *)arg);
+
+	case FS_IOC_GET_ENCRYPTION_NONCE:
+		ret = vet_mds_for_fscrypt(file);
+		if (ret)
+			return ret;
+		return fscrypt_ioctl_get_nonce(file, (void __user *)arg);
+	}
+
+	return -ENOTTY;
+}

linux-7.2.3/fs/ceph/ioctl.h

@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef FS_CEPH_IOCTL_H
+#define FS_CEPH_IOCTL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define CEPH_IOCTL_MAGIC 0x97
+
+/*
+ * CEPH_IOC_GET_LAYOUT - get file layout or dir layout policy
+ * CEPH_IOC_SET_LAYOUT - set file layout
+ * CEPH_IOC_SET_LAYOUT_POLICY - set dir layout policy
+ *
+ * The file layout specifies how file data is striped over objects in
+ * the distributed object store, which object pool they belong to (if
+ * it differs from the default), and an optional 'preferred osd' to
+ * store them on.
+ *
+ * Files get a new layout based on the policy set on the containing
+ * directory or one of its ancestors.  The GET_LAYOUT ioctl will let
+ * you examine the layout for a file or the policy on a directory.
+ *
+ * SET_LAYOUT will let you set a layout on a newly created file.  This
+ * only works immediately after the file is created and before any
+ * data is written to it.
+ *
+ * SET_LAYOUT_POLICY will let you set a layout policy (default layout)
+ * on a directory that will apply to any new files created in that
+ * directory (or any child directory that doesn't specify a layout of
+ * its own).
+ */
+
+/* use u64 to align sanely on all archs */
+struct ceph_ioctl_layout {
+	__u64 stripe_unit, stripe_count, object_size;
+	__u64 data_pool;
+
+	/* obsolete.  new values ignored, always return -1 */
+	__s64 preferred_osd;
+};
+
+#define CEPH_IOC_GET_LAYOUT _IOR(CEPH_IOCTL_MAGIC, 1,		\
+				   struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2,		\
+				   struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT_POLICY _IOW(CEPH_IOCTL_MAGIC, 5,	\
+				   struct ceph_ioctl_layout)
+
+/*
+ * CEPH_IOC_GET_DATALOC - get location of file data in the cluster
+ *
+ * Extract identity, address of the OSD and object storing a given
+ * file offset.
+ */
+struct ceph_ioctl_dataloc {
+	__u64 file_offset;           /* in+out: file offset */
+	__u64 object_offset;         /* out: offset in object */
+	__u64 object_no;             /* out: object # */
+	__u64 object_size;           /* out: object size */
+	char object_name[64];        /* out: object name */
+	__u64 block_offset;          /* out: offset in block */
+	__u64 block_size;            /* out: block length */
+	__s64 osd;                   /* out: osd # */
+	struct sockaddr_storage osd_addr; /* out: osd address */
+};
+
+#define CEPH_IOC_GET_DATALOC _IOWR(CEPH_IOCTL_MAGIC, 3,	\
+				   struct ceph_ioctl_dataloc)
+
+/*
+ * CEPH_IOC_LAZYIO - relax consistency
+ *
+ * Normally Ceph switches to synchronous IO when multiple clients have
+ * the file open (and or more for write).  Reads and writes bypass the
+ * page cache and go directly to the OSD.  Setting this flag on a file
+ * descriptor will allow buffered IO for this file in cases where the
+ * application knows it won't interfere with other nodes (or doesn't
+ * care).
+ */
+#define CEPH_IOC_LAZYIO _IO(CEPH_IOCTL_MAGIC, 4)
+
+/*
+ * CEPH_IOC_SYNCIO - force synchronous IO
+ *
+ * This ioctl sets a file flag that forces the synchronous IO that
+ * bypasses the page cache, even if it is not necessary.  This is
+ * essentially the opposite behavior of IOC_LAZYIO.  This forces the
+ * same read/write path as a file opened by multiple clients when one
+ * or more of those clients is opened for write.
+ *
+ * Note that this type of sync IO takes a different path than a file
+ * opened with O_SYNC/D_SYNC (writes hit the page cache and are
+ * immediately flushed on page boundaries).  It is very similar to
+ * O_DIRECT (writes bypass the page cache) excep that O_DIRECT writes
+ * are not copied (user page must remain stable) and O_DIRECT writes
+ * have alignment restrictions (on the buffer and file offset).
+ */
+#define CEPH_IOC_SYNCIO _IO(CEPH_IOCTL_MAGIC, 5)
+
+#endif

linux-7.2.3/fs/ceph/locks.c

@@ -0,0 +1,528 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/random.h>
+
+#include "super.h"
+#include "mds_client.h"
+#include <linux/filelock.h>
+#include <linux/ceph/pagelist.h>
+
+static u64 lock_secret;
+static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
+                                         struct ceph_mds_request *req);
+
+static inline u64 secure_addr(void *addr)
+{
+	u64 v = lock_secret ^ (u64)(unsigned long)addr;
+	/*
+	 * Set the most significant bit, so that MDS knows the 'owner'
+	 * is sufficient to identify the owner of lock. (old code uses
+	 * both 'owner' and 'pid')
+	 */
+	v |= (1ULL << 63);
+	return v;
+}
+
+void __init ceph_flock_init(void)
+{
+	get_random_bytes(&lock_secret, sizeof(lock_secret));
+}
+
+static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
+{
+	struct inode *inode = file_inode(dst->c.flc_file);
+	atomic_inc(&ceph_inode(inode)->i_filelock_ref);
+	dst->fl_u.ceph.inode = igrab(inode);
+}
+
+/*
+ * Do not use the 'fl->fl_file' in release function, which
+ * is possibly already released by another thread.
+ */
+static void ceph_fl_release_lock(struct file_lock *fl)
+{
+	struct inode *inode = fl->fl_u.ceph.inode;
+	struct ceph_inode_info *ci;
+
+	/*
+	 * If inode is NULL it should be a request file_lock,
+	 * nothing we can do.
+	 */
+	if (!inode)
+		return;
+
+	ci = ceph_inode(inode);
+	if (atomic_dec_and_test(&ci->i_filelock_ref)) {
+		/* clear error when all locks are released */
+		clear_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags);
+	}
+	fl->fl_u.ceph.inode = NULL;
+	iput(inode);
+}
+
+static const struct file_lock_operations ceph_fl_lock_ops = {
+	.fl_copy_lock = ceph_fl_copy_lock,
+	.fl_release_private = ceph_fl_release_lock,
+};
+
+/*
+ * Implement fcntl and flock locking functions.
+ */
+static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
+			     int cmd, u8 wait, struct file_lock *fl)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_mds_request *req;
+	int err;
+	u64 length = 0;
+	u64 owner;
+
+	if (operation == CEPH_MDS_OP_SETFILELOCK) {
+		/*
+		 * increasing i_filelock_ref closes race window between
+		 * handling request reply and adding file_lock struct to
+		 * inode. Otherwise, auth caps may get trimmed in the
+		 * window. Caller function will decrease the counter.
+		 */
+		fl->fl_ops = &ceph_fl_lock_ops;
+		fl->fl_ops->fl_copy_lock(fl, NULL);
+	}
+
+	if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK)
+		wait = 0;
+
+	req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = inode;
+	ihold(inode);
+	req->r_num_caps = 1;
+
+	/* mds requires start and length rather than start and end */
+	if (LLONG_MAX == fl->fl_end)
+		length = 0;
+	else
+		length = fl->fl_end - fl->fl_start + 1;
+
+	owner = secure_addr(fl->c.flc_owner);
+
+	doutc(cl, "rule: %d, op: %d, owner: %llx, pid: %llu, "
+		    "start: %llu, length: %llu, wait: %d, type: %d\n",
+		    (int)lock_type, (int)operation, owner,
+		    (u64) fl->c.flc_pid,
+		    fl->fl_start, length, wait, fl->c.flc_type);
+
+	req->r_args.filelock_change.rule = lock_type;
+	req->r_args.filelock_change.type = cmd;
+	req->r_args.filelock_change.owner = cpu_to_le64(owner);
+	req->r_args.filelock_change.pid = cpu_to_le64((u64) fl->c.flc_pid);
+	req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
+	req->r_args.filelock_change.length = cpu_to_le64(length);
+	req->r_args.filelock_change.wait = wait;
+
+	err = ceph_mdsc_submit_request(mdsc, inode, req);
+	if (!err)
+		err = ceph_mdsc_wait_request(mdsc, req, wait ?
+					ceph_lock_wait_for_completion : NULL);
+	if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
+		fl->c.flc_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
+			fl->c.flc_type = F_RDLCK;
+		else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
+			fl->c.flc_type = F_WRLCK;
+		else
+			fl->c.flc_type = F_UNLCK;
+
+		fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
+		length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
+						 le64_to_cpu(req->r_reply_info.filelock_reply->length);
+		if (length >= 1)
+			fl->fl_end = length -1;
+		else
+			fl->fl_end = 0;
+
+	}
+	ceph_mdsc_put_request(req);
+	doutc(cl, "rule: %d, op: %d, pid: %llu, start: %llu, "
+	      "length: %llu, wait: %d, type: %d, err code %d\n",
+	      (int)lock_type, (int)operation, (u64) fl->c.flc_pid,
+	      fl->fl_start, length, wait, fl->c.flc_type, err);
+	return err;
+}
+
+static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
+                                         struct ceph_mds_request *req)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_mds_request *intr_req;
+	struct inode *inode = req->r_inode;
+	int err, lock_type;
+
+	BUG_ON(req->r_op != CEPH_MDS_OP_SETFILELOCK);
+	if (req->r_args.filelock_change.rule == CEPH_LOCK_FCNTL)
+		lock_type = CEPH_LOCK_FCNTL_INTR;
+	else if (req->r_args.filelock_change.rule == CEPH_LOCK_FLOCK)
+		lock_type = CEPH_LOCK_FLOCK_INTR;
+	else
+		BUG_ON(1);
+	BUG_ON(req->r_args.filelock_change.type == CEPH_LOCK_UNLOCK);
+
+	err = wait_for_completion_interruptible(&req->r_completion);
+	if (!err)
+		return 0;
+
+	doutc(cl, "request %llu was interrupted\n", req->r_tid);
+
+	mutex_lock(&mdsc->mutex);
+	if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
+		err = 0;
+	} else {
+		/*
+		 * ensure we aren't running concurrently with
+		 * ceph_fill_trace or ceph_readdir_prepopulate, which
+		 * rely on locks (dir mutex) held by our caller.
+		 */
+		mutex_lock(&req->r_fill_mutex);
+		req->r_err = err;
+		set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
+		mutex_unlock(&req->r_fill_mutex);
+
+		if (!req->r_session) {
+			// haven't sent the request
+			err = 0;
+		}
+	}
+	mutex_unlock(&mdsc->mutex);
+	if (!err)
+		return 0;
+
+	intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK,
+					    USE_AUTH_MDS);
+	if (IS_ERR(intr_req))
+		return PTR_ERR(intr_req);
+
+	intr_req->r_inode = inode;
+	ihold(inode);
+	intr_req->r_num_caps = 1;
+
+	intr_req->r_args.filelock_change = req->r_args.filelock_change;
+	intr_req->r_args.filelock_change.rule = lock_type;
+	intr_req->r_args.filelock_change.type = CEPH_LOCK_UNLOCK;
+
+	err = ceph_mdsc_do_request(mdsc, inode, intr_req);
+	ceph_mdsc_put_request(intr_req);
+
+	if (err && err != -ERESTARTSYS)
+		return err;
+
+	err = wait_for_completion_killable(&req->r_safe_completion);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int try_unlock_file(struct file *file, struct file_lock *fl)
+{
+	int err;
+	unsigned int orig_flags = fl->c.flc_flags;
+	fl->c.flc_flags |= FL_EXISTS;
+	err = locks_lock_file_wait(file, fl);
+	fl->c.flc_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.
+ */
+int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int err = 0;
+	u16 op = CEPH_MDS_OP_SETFILELOCK;
+	u8 wait = 0;
+	u8 lock_cmd;
+
+	if (!(fl->c.flc_flags & FL_POSIX))
+		return -ENOLCK;
+
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
+	doutc(cl, "fl_owner: %p\n", fl->c.flc_owner);
+
+	/* set wait bit as appropriate, then make command as Ceph expects it*/
+	if (IS_GETLK(cmd))
+		op = CEPH_MDS_OP_GETFILELOCK;
+	else if (IS_SETLKW(cmd))
+		wait = 1;
+
+	if (test_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags)) {
+		if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl))
+			posix_lock_file(file, fl, NULL);
+		return -EIO;
+	}
+
+	/* Wait for reset to complete before acquiring new locks */
+	if (op == CEPH_MDS_OP_SETFILELOCK && !lock_is_unlock(fl)) {
+		err = ceph_mdsc_wait_for_reset(mdsc);
+		if (err)
+			return err;
+	}
+
+	if (lock_is_read(fl))
+		lock_cmd = CEPH_LOCK_SHARED;
+	else if (lock_is_write(fl))
+		lock_cmd = CEPH_LOCK_EXCL;
+	else
+		lock_cmd = CEPH_LOCK_UNLOCK;
+
+	if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl)) {
+		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 && F_UNLCK != fl->c.flc_type) {
+			doutc(cl, "locking locally\n");
+			err = posix_lock_file(file, fl, NULL);
+			if (err) {
+				/* undo! This should only happen if
+				 * the kernel detects local
+				 * deadlock. */
+				ceph_lock_message(CEPH_LOCK_FCNTL, op, inode,
+						  CEPH_LOCK_UNLOCK, 0, fl);
+				doutc(cl, "got %d on posix_lock_file, undid lock\n",
+				      err);
+			}
+		}
+	}
+	return err;
+}
+
+int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int err = 0;
+	u8 wait = 0;
+	u8 lock_cmd;
+
+	if (!(fl->c.flc_flags & FL_FLOCK))
+		return -ENOLCK;
+
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
+	doutc(cl, "fl_file: %p\n", fl->c.flc_file);
+
+	if (test_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags)) {
+		if (lock_is_unlock(fl))
+			locks_lock_file_wait(file, fl);
+		return -EIO;
+	}
+
+	/* Wait for reset to complete before acquiring new locks */
+	if (!lock_is_unlock(fl)) {
+		err = ceph_mdsc_wait_for_reset(mdsc);
+		if (err)
+			return err;
+	}
+
+	if (IS_SETLKW(cmd))
+		wait = 1;
+
+	if (lock_is_read(fl))
+		lock_cmd = CEPH_LOCK_SHARED;
+	else if (lock_is_write(fl))
+		lock_cmd = CEPH_LOCK_EXCL;
+	else
+		lock_cmd = CEPH_LOCK_UNLOCK;
+
+	if (lock_is_unlock(fl)) {
+		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 && F_UNLCK != fl->c.flc_type) {
+		err = locks_lock_file_wait(file, fl);
+		if (err) {
+			ceph_lock_message(CEPH_LOCK_FLOCK,
+					  CEPH_MDS_OP_SETFILELOCK,
+					  inode, CEPH_LOCK_UNLOCK, 0, fl);
+			doutc(cl, "got %d on locks_lock_file_wait, undid lock\n",
+			      err);
+		}
+	}
+	return err;
+}
+
+/*
+ * Fills in the passed counter variables, so you can prepare pagelist metadata
+ * before calling ceph_encode_locks.
+ */
+void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	struct file_lock *lock;
+	struct file_lock_context *ctx;
+
+	*fcntl_count = 0;
+	*flock_count = 0;
+
+	ctx = locks_inode_context(inode);
+	if (ctx) {
+		spin_lock(&ctx->flc_lock);
+		for_each_file_lock(lock, &ctx->flc_posix)
+			++(*fcntl_count);
+		for_each_file_lock(lock, &ctx->flc_flock)
+			++(*flock_count);
+		spin_unlock(&ctx->flc_lock);
+	}
+	doutc(cl, "counted %d flock locks and %d fcntl locks\n",
+	      *flock_count, *fcntl_count);
+}
+
+/*
+ * Given a pointer to a lock, convert it to a ceph filelock
+ */
+static int lock_to_ceph_filelock(struct inode *inode,
+				 struct file_lock *lock,
+				 struct ceph_filelock *cephlock)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int err = 0;
+
+	cephlock->start = cpu_to_le64(lock->fl_start);
+	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
+	cephlock->client = cpu_to_le64(0);
+	cephlock->pid = cpu_to_le64((u64) lock->c.flc_pid);
+	cephlock->owner = cpu_to_le64(secure_addr(lock->c.flc_owner));
+
+	switch (lock->c.flc_type) {
+	case F_RDLCK:
+		cephlock->type = CEPH_LOCK_SHARED;
+		break;
+	case F_WRLCK:
+		cephlock->type = CEPH_LOCK_EXCL;
+		break;
+	case F_UNLCK:
+		cephlock->type = CEPH_LOCK_UNLOCK;
+		break;
+	default:
+		doutc(cl, "Have unknown lock type %d\n",
+		      lock->c.flc_type);
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+/*
+ * Encode the flock and fcntl locks for the given inode into the ceph_filelock
+ * array. Must be called with inode->i_lock already held.
+ * If we encounter more of a specific lock type than expected, return -ENOSPC.
+ */
+int ceph_encode_locks_to_buffer(struct inode *inode,
+				struct ceph_filelock *flocks,
+				int num_fcntl_locks, int num_flock_locks)
+{
+	struct file_lock *lock;
+	struct file_lock_context *ctx = locks_inode_context(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int err = 0;
+	int seen_fcntl = 0;
+	int seen_flock = 0;
+	int l = 0;
+
+	doutc(cl, "encoding %d flock and %d fcntl locks\n", num_flock_locks,
+	      num_fcntl_locks);
+
+	if (!ctx)
+		return 0;
+
+	spin_lock(&ctx->flc_lock);
+	for_each_file_lock(lock, &ctx->flc_posix) {
+		++seen_fcntl;
+		if (seen_fcntl > num_fcntl_locks) {
+			err = -ENOSPC;
+			goto fail;
+		}
+		err = lock_to_ceph_filelock(inode, lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
+	}
+	for_each_file_lock(lock, &ctx->flc_flock) {
+		++seen_flock;
+		if (seen_flock > num_flock_locks) {
+			err = -ENOSPC;
+			goto fail;
+		}
+		err = lock_to_ceph_filelock(inode, lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
+	}
+fail:
+	spin_unlock(&ctx->flc_lock);
+	return err;
+}
+
+/*
+ * Copy the encoded flock and fcntl locks into the pagelist.
+ * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
+ * sequential flock locks.
+ * Returns zero on success.
+ */
+int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+			   struct ceph_pagelist *pagelist,
+			   int num_fcntl_locks, int num_flock_locks)
+{
+	int err = 0;
+	__le32 nlocks;
+
+	nlocks = cpu_to_le32(num_fcntl_locks);
+	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+	if (err)
+		goto out_fail;
+
+	if (num_fcntl_locks > 0) {
+		err = ceph_pagelist_append(pagelist, flocks,
+					   num_fcntl_locks * sizeof(*flocks));
+		if (err)
+			goto out_fail;
+	}
+
+	nlocks = cpu_to_le32(num_flock_locks);
+	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+	if (err)
+		goto out_fail;
+
+	if (num_flock_locks > 0) {
+		err = ceph_pagelist_append(pagelist, &flocks[num_fcntl_locks],
+					   num_flock_locks * sizeof(*flocks));
+	}
+out_fail:
+	return err;
+}

linux-7.2.3/fs/ceph/mds_client.h

@@ -0,0 +1,733 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_MDS_CLIENT_H
+#define _FS_CEPH_MDS_CLIENT_H
+
+#include <linux/completion.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
+#include <linux/utsname.h>
+#include <linux/ktime.h>
+
+#include <linux/ceph/types.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/auth.h>
+
+#include "mdsmap.h"
+#include "metric.h"
+#include "subvolume_metrics.h"
+#include "super.h"
+
+/* The first 8 bits are reserved for old ceph releases */
+enum ceph_feature_type {
+	CEPHFS_FEATURE_MIMIC = 8,
+	CEPHFS_FEATURE_REPLY_ENCODING,
+	CEPHFS_FEATURE_RECLAIM_CLIENT,
+	CEPHFS_FEATURE_LAZY_CAP_WANTED,
+	CEPHFS_FEATURE_MULTI_RECONNECT,
+	CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_METRIC_COLLECT,
+	CEPHFS_FEATURE_ALTERNATE_NAME,
+	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,
+	CEPHFS_FEATURE_OP_GETVXATTR,
+	CEPHFS_FEATURE_32BITS_RETRY_FWD,
+	CEPHFS_FEATURE_NEW_SNAPREALM_INFO,
+	CEPHFS_FEATURE_HAS_OWNER_UIDGID,
+	CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK,
+	CEPHFS_FEATURE_SUBVOLUME_METRICS,
+
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_SUBVOLUME_METRICS,
+};
+
+#define CEPHFS_FEATURES_CLIENT_SUPPORTED {	\
+	0, 1, 2, 3, 4, 5, 6, 7,			\
+	CEPHFS_FEATURE_MIMIC,			\
+	CEPHFS_FEATURE_REPLY_ENCODING,		\
+	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
+	CEPHFS_FEATURE_MULTI_RECONNECT,		\
+	CEPHFS_FEATURE_DELEG_INO,		\
+	CEPHFS_FEATURE_METRIC_COLLECT,		\
+	CEPHFS_FEATURE_ALTERNATE_NAME,		\
+	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,	\
+	CEPHFS_FEATURE_OP_GETVXATTR,		\
+	CEPHFS_FEATURE_32BITS_RETRY_FWD,	\
+	CEPHFS_FEATURE_HAS_OWNER_UIDGID,	\
+	CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK,	\
+	CEPHFS_FEATURE_SUBVOLUME_METRICS,	\
+}
+
+/*
+ * Some lock dependencies:
+ *
+ * session->s_mutex
+ *         mdsc->mutex
+ *
+ *         mdsc->snap_rwsem
+ *
+ *         ci->i_ceph_lock
+ *                 mdsc->snap_flush_lock
+ *                 mdsc->cap_delay_lock
+ *
+ */
+
+struct ceph_fs_client;
+struct ceph_cap;
+
+#define MDS_AUTH_UID_ANY -1
+#define CEPH_GET_CAPS_WAIT_TIMEOUT (5 * HZ)
+#define CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC 60
+#define CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES 5
+#define CEPH_CAP_FLUSH_MAX_DUMP_ITERS 5
+#define CEPH_CLIENT_RESET_REASON_LEN	64
+#define CEPH_CLIENT_RESET_DRAIN_SEC	30
+#define CEPH_CLIENT_RESET_CLOSE_GRACE_MS 100
+#define CEPH_CLIENT_RESET_WAIT_TIMEOUT_SEC 120
+
+enum ceph_client_reset_phase {
+	CEPH_CLIENT_RESET_IDLE = 0,
+	/*
+	 * QUIESCING is set synchronously by schedule_reset() before the
+	 * workqueue item is dispatched.  It gates new requests (any
+	 * phase != IDLE blocks callers) during the window between
+	 * scheduling and the work function's transition to DRAINING.
+	 */
+	CEPH_CLIENT_RESET_QUIESCING,
+	CEPH_CLIENT_RESET_DRAINING,
+	CEPH_CLIENT_RESET_TEARDOWN,
+};
+
+struct ceph_client_reset_state {
+	spinlock_t lock;		/* protects all fields below */
+	u64 trigger_count;		/* number of resets triggered */
+	u64 success_count;		/* number of successful resets */
+	u64 failure_count;		/* number of failed resets */
+	unsigned long last_start;	/* jiffies when last reset started */
+	unsigned long last_finish;	/* jiffies when last reset finished */
+	int last_errno;			/* result of most recent reset */
+	enum ceph_client_reset_phase phase; /* current reset phase */
+	bool drain_timed_out;		/* drain exceeded timeout */
+	bool shutdown;			/* destroy in progress */
+	int sessions_reset;		/* sessions torn down in last reset */
+	char last_reason[CEPH_CLIENT_RESET_REASON_LEN]; /* operator-supplied reason */
+
+	/* Request blocking during reset */
+	wait_queue_head_t blocked_wq;	/* waitqueue for blocked callers */
+	atomic_t blocked_requests;	/* count of blocked callers */
+};
+
+static inline bool ceph_reset_is_idle(struct ceph_client_reset_state *st)
+{
+	return READ_ONCE(st->phase) == CEPH_CLIENT_RESET_IDLE;
+}
+
+struct ceph_mds_cap_match {
+	s64 uid;  /* default to MDS_AUTH_UID_ANY */
+	u32 num_gids;
+	u32 *gids;  /* use these GIDs */
+	char *path;  /* require path to be child of this
+			(may be "" or "/" for any) */
+	char *fs_name;
+	bool root_squash;  /* default to false */
+};
+
+struct ceph_mds_cap_auth {
+	struct ceph_mds_cap_match match;
+	bool readable;
+	bool writeable;
+};
+
+/*
+ * parsed info about a single inode.  pointers are into the encoded
+ * on-wire structures within the mds reply message payload.
+ */
+struct ceph_mds_reply_info_in {
+	struct ceph_mds_reply_inode *in;
+	struct ceph_dir_layout dir_layout;
+	u32 symlink_len;
+	char *symlink;
+	u32 xattr_len;
+	char *xattr_data;
+	u64 inline_version;
+	u32 inline_len;
+	char *inline_data;
+	u32 pool_ns_len;
+	char *pool_ns_data;
+	u64 max_bytes;
+	u64 max_files;
+	s32 dir_pin;
+	struct ceph_timespec btime;
+	struct ceph_timespec snap_btime;
+	u8 *fscrypt_auth;
+	u8 *fscrypt_file;
+	u32 fscrypt_auth_len;
+	u32 fscrypt_file_len;
+	u64 rsnaps;
+	u64 change_attr;
+	u64 subvolume_id;
+};
+
+struct ceph_mds_reply_dir_entry {
+	bool			      is_nokey;
+	char                          *name;
+	u32                           name_len;
+	u32			      raw_hash;
+	struct ceph_mds_reply_lease   *lease;
+	struct ceph_mds_reply_info_in inode;
+	loff_t			      offset;
+};
+
+struct ceph_mds_reply_xattr {
+	char *xattr_value;
+	size_t xattr_value_len;
+};
+
+/*
+ * parsed info about an mds reply, including information about
+ * either: 1) the target inode and/or its parent directory and dentry,
+ * and directory contents (for readdir results), or
+ * 2) the file range lock info (for fcntl F_GETLK results).
+ */
+struct ceph_mds_reply_info_parsed {
+	struct ceph_mds_reply_head    *head;
+
+	/* trace */
+	struct ceph_mds_reply_info_in diri, targeti;
+	struct ceph_mds_reply_dirfrag *dirfrag;
+	char                          *dname;
+	u8			      *altname;
+	u32                           dname_len;
+	u32                           altname_len;
+	struct ceph_mds_reply_lease   *dlease;
+	struct ceph_mds_reply_xattr   xattr_info;
+
+	/* extra */
+	union {
+		/* for fcntl F_GETLK results */
+		struct ceph_filelock *filelock_reply;
+
+		/* for readdir results */
+		struct {
+			struct ceph_mds_reply_dirfrag *dir_dir;
+			size_t			      dir_buf_size;
+			int                           dir_nr;
+			bool			      dir_end;
+			bool			      dir_complete;
+			bool			      hash_order;
+			bool			      offset_hash;
+			struct ceph_mds_reply_dir_entry  *dir_entries;
+		};
+
+		/* for create results */
+		struct {
+			bool has_create_ino;
+			u64 ino;
+		};
+	};
+
+	/* encoded blob describing snapshot contexts for certain
+	   operations (e.g., open) */
+	void *snapblob;
+	int snapblob_len;
+};
+
+
+/*
+ * cap releases are batched and sent to the MDS en masse.
+ *
+ * Account for per-message overhead of mds_cap_release header
+ * and __le32 for osd epoch barrier trailing field.
+ */
+#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - sizeof(u32) -		\
+				sizeof(struct ceph_mds_cap_release)) /	\
+			        sizeof(struct ceph_mds_cap_item))
+
+
+/*
+ * state associated with each MDS<->client session
+ */
+enum {
+	CEPH_MDS_SESSION_NEW = 1,
+	CEPH_MDS_SESSION_OPENING = 2,
+	CEPH_MDS_SESSION_OPEN = 3,
+	CEPH_MDS_SESSION_HUNG = 4,
+	CEPH_MDS_SESSION_RESTARTING = 5,
+	CEPH_MDS_SESSION_RECONNECTING = 6,
+	CEPH_MDS_SESSION_CLOSING = 7,
+	CEPH_MDS_SESSION_CLOSED = 8,
+	CEPH_MDS_SESSION_REJECTED = 9,
+};
+
+struct ceph_mds_session {
+	struct ceph_mds_client *s_mdsc;
+	int               s_mds;
+	int               s_state;
+	unsigned long     s_ttl;      /* time until mds kills us */
+	unsigned long	  s_features;
+	u64               s_seq;      /* incoming msg seq # */
+	struct mutex      s_mutex;    /* serialize session messages */
+
+	struct ceph_connection s_con;
+
+	struct ceph_auth_handshake s_auth;
+
+	atomic_t          s_cap_gen;  /* inc each time we get mds stale msg */
+	unsigned long     s_cap_ttl;  /* when session caps expire. protected by s_mutex */
+
+	/* protected by s_cap_lock */
+	spinlock_t        s_cap_lock;
+	refcount_t        s_ref;
+	struct list_head  s_caps;     /* all caps issued by this session */
+	struct ceph_cap  *s_cap_iterator;
+	int               s_nr_caps;
+	int               s_num_cap_releases;
+	int		  s_cap_reconnect;
+	int		  s_readonly;
+	struct list_head  s_cap_releases; /* waiting cap_release messages */
+	struct work_struct s_cap_release_work;
+
+	/* See ceph_inode_info->i_dirty_item. */
+	struct list_head  s_cap_dirty;	      /* inodes w/ dirty caps */
+
+	/* See ceph_inode_info->i_flushing_item. */
+	struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */
+
+	unsigned long     s_renew_requested; /* last time we sent a renew req */
+	u64               s_renew_seq;
+
+	struct list_head  s_waiting;  /* waiting requests */
+	struct list_head  s_unsafe;   /* unsafe requests */
+	struct xarray	  s_delegated_inos;
+};
+
+/*
+ * modes of choosing which MDS to send a request to
+ */
+enum {
+	USE_ANY_MDS,
+	USE_RANDOM_MDS,
+	USE_AUTH_MDS,   /* prefer authoritative mds for this metadata item */
+};
+
+struct ceph_mds_request;
+struct ceph_mds_client;
+
+/*
+ * request completion callback
+ */
+typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
+					     struct ceph_mds_request *req);
+/*
+ * wait for request completion callback
+ */
+typedef int (*ceph_mds_request_wait_callback_t) (struct ceph_mds_client *mdsc,
+						 struct ceph_mds_request *req);
+
+/*
+ * an in-flight mds request
+ */
+struct ceph_mds_request {
+	u64 r_tid;                   /* transaction id */
+	struct rb_node r_node;
+	struct ceph_mds_client *r_mdsc;
+
+	struct kref       r_kref;
+	int r_op;                    /* mds op code */
+
+	/* operation on what? */
+	struct inode *r_inode;              /* arg1 */
+	struct dentry *r_dentry;            /* arg1 */
+	struct dentry *r_old_dentry;        /* arg2: rename from or link from */
+	struct inode *r_old_dentry_dir;     /* arg2: old dentry's parent dir */
+	char *r_path1, *r_path2;
+	struct ceph_vino r_ino1, r_ino2;
+
+	struct inode *r_parent;		    /* parent dir inode */
+	struct inode *r_target_inode;       /* resulting inode */
+	struct inode *r_new_inode;	    /* new inode (for creates) */
+
+	const struct qstr *r_dname;	    /* stable name (for ->d_revalidate) */
+
+#define CEPH_MDS_R_DIRECT_IS_HASH	(1) /* r_direct_hash is valid */
+#define CEPH_MDS_R_ABORTED		(2) /* call was aborted */
+#define CEPH_MDS_R_GOT_UNSAFE		(3) /* got an unsafe reply */
+#define CEPH_MDS_R_GOT_SAFE		(4) /* got a safe reply */
+#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 */
+#define CEPH_MDS_R_FSCRYPT_FILE		(9) /* must marshal fscrypt_file field */
+	unsigned long	r_req_flags;
+
+	struct mutex r_fill_mutex;
+
+	union ceph_mds_request_args r_args;
+
+	struct ceph_fscrypt_auth *r_fscrypt_auth;
+	u64	r_fscrypt_file;
+
+	u8 *r_altname;		    /* fscrypt binary crypttext for long filenames */
+	u32 r_altname_len;	    /* length of r_altname */
+
+	int r_fmode;        /* file mode, if expecting cap */
+	int r_request_release_offset;
+	const struct cred *r_cred;
+	struct mnt_idmap *r_mnt_idmap;
+	struct timespec64 r_stamp;
+
+	/* for choosing which mds to send this request to */
+	int r_direct_mode;
+	u32 r_direct_hash;      /* choose dir frag based on this dentry hash */
+
+	/* data payload is used for xattr ops */
+	struct ceph_pagelist *r_pagelist;
+
+	/* what caps shall we drop? */
+	int r_inode_drop, r_inode_unless;
+	int r_dentry_drop, r_dentry_unless;
+	int r_old_dentry_drop, r_old_dentry_unless;
+	struct inode *r_old_inode;
+	int r_old_inode_drop, r_old_inode_unless;
+
+	struct ceph_msg  *r_request;  /* original request */
+	struct ceph_msg  *r_reply;
+	struct ceph_mds_reply_info_parsed r_reply_info;
+	int r_err;
+	u32               r_readdir_offset;
+
+	struct page *r_locked_page;
+	int r_dir_caps;
+	int r_num_caps;
+
+	unsigned long r_timeout;  /* optional.  jiffies, 0 is "wait forever" */
+	unsigned long r_started;  /* start time to measure timeout against */
+	unsigned long r_start_latency;  /* start time to measure latency */
+	unsigned long r_end_latency;    /* finish time to measure latency */
+	unsigned long r_request_started; /* start time for mds request only,
+					    used to measure lease durations */
+
+	/* link unsafe requests to parent directory, for fsync */
+	struct inode	*r_unsafe_dir;
+	struct list_head r_unsafe_dir_item;
+
+	/* unsafe requests that modify the target inode */
+	struct list_head r_unsafe_target_item;
+
+	struct ceph_mds_session *r_session;
+
+	int               r_attempts;   /* resend attempts */
+	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;
+	struct completion r_safe_completion;
+	ceph_mds_request_callback_t r_callback;
+	struct list_head  r_unsafe_item;  /* per-session unsafe list item */
+
+	long long	  r_dir_release_cnt;
+	long long	  r_dir_ordered_cnt;
+	int		  r_readdir_cache_idx;
+
+	int		  r_feature_needed;
+
+	struct ceph_cap_reservation r_caps_reservation;
+};
+
+struct ceph_pool_perm {
+	struct rb_node node;
+	int perm;
+	s64 pool;
+	size_t pool_ns_len;
+	char pool_ns[];
+};
+
+struct ceph_snapid_map {
+	struct rb_node node;
+	struct list_head lru;
+	atomic_t ref;
+	dev_t dev;
+	u64 snap;
+	unsigned long last_used;
+};
+
+/*
+ * node for list of quotarealm inodes that are not visible from the filesystem
+ * mountpoint, but required to handle, e.g. quotas.
+ */
+struct ceph_quotarealm_inode {
+	struct rb_node node;
+	u64 ino;
+	unsigned long timeout; /* last time a lookup failed for this inode */
+	struct mutex mutex;
+	struct inode *inode;
+};
+
+#ifdef CONFIG_DEBUG_FS
+
+struct cap_wait {
+	struct list_head	list;
+	u64			ino;
+	pid_t			tgid;
+	int			need;
+	int			want;
+};
+
+#endif
+
+enum {
+	CEPH_MDSC_STOPPING_BEGIN = 1,
+	CEPH_MDSC_STOPPING_FLUSHING = 2,
+	CEPH_MDSC_STOPPING_FLUSHED = 3,
+};
+
+/*
+ * mds client state
+ */
+struct ceph_mds_client {
+	struct ceph_fs_client  *fsc;
+	struct mutex            mutex;         /* all nested structures */
+
+	struct ceph_mdsmap      *mdsmap;
+	struct completion       safe_umount_waiters;
+	wait_queue_head_t       session_close_wq;
+	struct list_head        waiting_for_map;
+	int 			mdsmap_err;
+
+	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
+	atomic_t		num_sessions;
+	int                     max_sessions;  /* len of sessions array */
+
+	spinlock_t              stopping_lock;  /* protect snap_empty */
+	int                     stopping;      /* the stage of shutting down */
+	atomic_t                stopping_blockers;
+	struct completion	stopping_waiter;
+
+	atomic64_t		dirty_folios;
+	wait_queue_head_t	flush_end_wq;
+
+	atomic64_t		quotarealms_count; /* # realms with quota */
+	/*
+	 * We keep a list of inodes we don't see in the mountpoint but that we
+	 * need to track quota realms.
+	 */
+	struct rb_root		quotarealms_inodes;
+	struct mutex		quotarealms_inodes_mutex;
+
+	/*
+	 * snap_rwsem will cover cap linkage into snaprealms, and
+	 * realm snap contexts.  (later, we can do per-realm snap
+	 * contexts locks..)  the empty list contains realms with no
+	 * references (implying they contain no inodes with caps) that
+	 * should be destroyed.
+	 */
+	u64			last_snap_seq;
+	struct rw_semaphore     snap_rwsem;
+	struct rb_root          snap_realms;
+	struct list_head        snap_empty;
+	int			num_snap_realms;
+	spinlock_t              snap_empty_lock;  /* protect snap_empty */
+
+	u64                    last_tid;      /* most recent mds request */
+	u64                    oldest_tid;    /* oldest incomplete mds request,
+						 excluding setfilelock requests */
+	struct rb_root         request_tree;  /* pending mds requests */
+	struct delayed_work    delayed_work;  /* delayed work */
+	unsigned long    last_renew_caps;  /* last time we renewed our caps */
+	struct list_head cap_delay_list;   /* caps with delayed release */
+	struct list_head cap_unlink_delay_list;  /* caps with delayed release for unlink */
+	spinlock_t       cap_delay_lock;   /* protects cap_delay_list and cap_unlink_delay_list */
+	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
+	spinlock_t       snap_flush_lock;
+
+	u64               last_cap_flush_tid;
+	struct list_head  cap_flush_list;
+	struct list_head  cap_dirty_migrating; /* ...that are migration... */
+	int               num_cap_flushing; /* # caps we are flushing */
+	spinlock_t        cap_dirty_lock;   /* protects above items */
+	wait_queue_head_t cap_flushing_wq;
+
+	struct work_struct cap_reclaim_work;
+	atomic_t	   cap_reclaim_pending;
+
+	struct work_struct cap_unlink_work;
+
+	/*
+	 * Cap reservations
+	 *
+	 * Maintain a global pool of preallocated struct ceph_caps, referenced
+	 * by struct ceph_caps_reservations.  This ensures that we preallocate
+	 * memory needed to successfully process an MDS response.  (If an MDS
+	 * sends us cap information and we fail to process it, we will have
+	 * problems due to the client and MDS being out of sync.)
+	 *
+	 * Reservations are 'owned' by a ceph_cap_reservation context.
+	 */
+	spinlock_t	caps_list_lock;
+	struct		list_head caps_list; /* unused (reserved or
+						unreserved) */
+#ifdef CONFIG_DEBUG_FS
+	struct		list_head cap_wait_list;
+#endif
+	int		caps_total_count;    /* total caps allocated */
+	int		caps_use_count;      /* in use */
+	int		caps_use_max;	     /* max used caps */
+	int		caps_reserve_count;  /* unused, reserved */
+	int		caps_avail_count;    /* unused, unreserved */
+	int		caps_min_count;      /* keep at least this many
+						(unreserved) */
+	spinlock_t	  dentry_list_lock;
+	struct list_head  dentry_leases;     /* fifo list */
+	struct list_head  dentry_dir_leases; /* lru list */
+
+	struct ceph_client_metric metric;
+	struct work_struct	reset_work;
+	struct ceph_client_reset_state reset_state;
+	struct ceph_subvolume_metrics_tracker subvol_metrics;
+
+	/* Subvolume metrics send tracking */
+	struct mutex		subvol_metrics_last_mutex;
+	struct ceph_subvol_metric_snapshot *subvol_metrics_last;
+	u32			subvol_metrics_last_nr;
+	u64			subvol_metrics_sent;
+	u64			subvol_metrics_nonzero_sends;
+
+	spinlock_t		snapid_map_lock;
+	struct rb_root		snapid_map_tree;
+	struct list_head	snapid_map_lru;
+
+	struct rw_semaphore     pool_perm_rwsem;
+	struct rb_root		pool_perm_tree;
+
+	u32			 s_cap_auths_num;
+	struct ceph_mds_cap_auth *s_cap_auths;
+
+	char nodename[__NEW_UTS_LEN + 1];
+};
+
+extern const char *ceph_mds_op_name(int op);
+
+extern bool check_session_state(struct ceph_mds_session *s);
+void inc_session_sequence(struct ceph_mds_session *s);
+
+extern struct ceph_mds_session *
+__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
+
+extern const char *ceph_session_state_name(int s);
+extern const char *ceph_reset_phase_name(enum ceph_client_reset_phase phase);
+
+extern struct ceph_mds_session *
+ceph_get_mds_session(struct ceph_mds_session *s);
+extern void ceph_put_mds_session(struct ceph_mds_session *s);
+int ceph_mdsc_schedule_reset(struct ceph_mds_client *mdsc,
+			     const char *reason);
+int ceph_mdsc_wait_for_reset(struct ceph_mds_client *mdsc);
+
+extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
+extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
+
+extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
+
+extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
+extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
+					   struct inode *dir);
+extern struct ceph_mds_request *
+ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
+extern int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
+				    struct inode *dir,
+				    struct ceph_mds_request *req);
+int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc,
+			struct ceph_mds_request *req,
+			ceph_mds_request_wait_callback_t wait_func);
+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);
+extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req);
+static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
+{
+	kref_get(&req->r_kref);
+}
+extern void ceph_mdsc_release_request(struct kref *kref);
+static inline void ceph_mdsc_put_request(struct ceph_mds_request *req)
+{
+	kref_put(&req->r_kref, ceph_mdsc_release_request);
+}
+
+extern void send_flush_mdlog(struct ceph_mds_session *s);
+extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc,
+				       void (*cb)(struct ceph_mds_session *),
+				       bool check_state);
+extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq);
+extern void __ceph_queue_cap_release(struct ceph_mds_session *session,
+				    struct ceph_cap *cap);
+extern void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc,
+					    struct ceph_mds_session *session);
+extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc);
+extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr);
+extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc);
+extern int ceph_iterate_session_caps(struct ceph_mds_session *session,
+				     int (*cb)(struct inode *, int mds, void *),
+				     void *arg);
+extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath,
+				 int mask);
+
+extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
+
+/*
+ * Structure to group path-related output parameters for build_*_path functions
+ */
+struct ceph_path_info {
+	const char *path;
+	int pathlen;
+	struct ceph_vino vino;
+	bool freepath;
+};
+
+static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info)
+{
+	if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path))
+		__putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen));
+}
+
+extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc,
+				  struct dentry *dentry, struct ceph_path_info *path_info,
+				  int for_wire);
+
+extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
+extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
+				     struct dentry *dentry, char action,
+				     u32 seq);
+
+extern void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc,
+				    struct ceph_msg *msg);
+extern void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc,
+				   struct ceph_msg *msg);
+
+extern struct ceph_mds_session *
+ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target);
+
+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_I_ASYNC_CREATE_BIT,
+			   TASK_KILLABLE);
+}
+
+extern int ceph_wait_on_conflict_unlink(struct dentry *dentry);
+extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session);
+extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino);
+
+extern bool enable_unsafe_idmap;
+#endif

linux-7.2.3/fs/ceph/mdsmap.c

@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+
+#include "mdsmap.h"
+#include "mds_client.h"
+#include "super.h"
+
+#define CEPH_MDS_IS_READY(i, ignore_laggy) \
+	(m->m_info[i].state > 0 && (ignore_laggy ? true : !m->m_info[i].laggy))
+
+static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy)
+{
+	int n = 0;
+	int i, j;
+
+	/* count */
+	for (i = 0; i < m->possible_max_rank; i++)
+		if (CEPH_MDS_IS_READY(i, ignore_laggy))
+			n++;
+	if (n == 0)
+		return -1;
+
+	/* pick */
+	n = get_random_u32_below(n);
+	for (j = 0, i = 0; i < m->possible_max_rank; i++) {
+		if (CEPH_MDS_IS_READY(i, ignore_laggy))
+			j++;
+		if (j > n)
+			break;
+	}
+
+	return i;
+}
+
+/*
+ * choose a random mds that is "up" (i.e. has a state > 0), or -1.
+ */
+int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
+{
+	int mds;
+
+	mds = __mdsmap_get_random_mds(m, false);
+	if (mds == m->possible_max_rank || mds == -1)
+		mds = __mdsmap_get_random_mds(m, true);
+
+	return mds == m->possible_max_rank ? -1 : mds;
+}
+
+#define __decode_and_drop_type(p, end, type, bad)		\
+	do {							\
+		if (*p + sizeof(type) > end)			\
+			goto bad;				\
+		*p += sizeof(type);				\
+	} while (0)
+
+#define __decode_and_drop_set(p, end, type, bad)		\
+	do {							\
+		u32 n;						\
+		size_t need;					\
+		ceph_decode_32_safe(p, end, n, bad);		\
+		need = sizeof(type) * n;			\
+		ceph_decode_need(p, end, need, bad);		\
+		*p += need;					\
+	} while (0)
+
+#define __decode_and_drop_map(p, end, ktype, vtype, bad)	\
+	do {							\
+		u32 n;						\
+		size_t need;					\
+		ceph_decode_32_safe(p, end, n, bad);		\
+		need = (sizeof(ktype) + sizeof(vtype)) * n;	\
+		ceph_decode_need(p, end, need, bad);		\
+		*p += need;					\
+	} while (0)
+
+
+static int __decode_and_drop_compat_set(void **p, void* end)
+{
+	int i;
+	/* compat, ro_compat, incompat*/
+	for (i = 0; i < 3; i++) {
+		u32 n;
+		ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
+		/* mask */
+		*p += sizeof(u64);
+		/* names (map<u64, string>) */
+		n = ceph_decode_32(p);
+		while (n-- > 0) {
+			u32 len;
+			ceph_decode_need(p, end, sizeof(u64) + sizeof(u32),
+					 bad);
+			*p += sizeof(u64);
+			len = ceph_decode_32(p);
+			ceph_decode_need(p, end, len, bad);
+			*p += len;
+		}
+	}
+	return 0;
+bad:
+	return -1;
+}
+
+/*
+ * Decode an MDS map
+ *
+ * Ignore any fields we don't care about (there are quite a few of
+ * them).
+ */
+struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
+				       void *end, bool msgr2)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_mdsmap *m;
+	const void *start = *p;
+	int i, j, n;
+	int err;
+	u8 mdsmap_v;
+	u16 mdsmap_ev;
+	u32 target;
+
+	m = kzalloc_obj(*m, GFP_NOFS);
+	if (!m)
+		return ERR_PTR(-ENOMEM);
+
+	ceph_decode_need(p, end, 1 + 1, bad);
+	mdsmap_v = ceph_decode_8(p);
+	*p += sizeof(u8);			/* mdsmap_cv */
+	if (mdsmap_v >= 4) {
+	       u32 mdsmap_len;
+	       ceph_decode_32_safe(p, end, mdsmap_len, bad);
+	       if (end < *p + mdsmap_len)
+		       goto bad;
+	       end = *p + mdsmap_len;
+	}
+
+	ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad);
+	m->m_epoch = ceph_decode_32(p);
+	m->m_client_epoch = ceph_decode_32(p);
+	m->m_last_failure = ceph_decode_32(p);
+	m->m_root = ceph_decode_32(p);
+	m->m_session_timeout = ceph_decode_32(p);
+	m->m_session_autoclose = ceph_decode_32(p);
+	m->m_max_file_size = ceph_decode_64(p);
+	m->m_max_mds = ceph_decode_32(p);
+
+	/*
+	 * pick out the active nodes as the m_num_active_mds, the
+	 * m_num_active_mds maybe larger than m_max_mds when decreasing
+	 * the max_mds in cluster side, in other case it should less
+	 * than or equal to m_max_mds.
+	 */
+	m->m_num_active_mds = n = ceph_decode_32(p);
+
+	/*
+	 * the possible max rank, it maybe larger than the m_num_active_mds,
+	 * for example if the mds_max == 2 in the cluster, when the MDS(0)
+	 * was laggy and being replaced by a new MDS, we will temporarily
+	 * receive a new mds map with n_num_mds == 1 and the active MDS(1),
+	 * and the mds rank >= m_num_active_mds.
+	 */
+	m->possible_max_rank = max(m->m_num_active_mds, m->m_max_mds);
+
+	m->m_info = kzalloc_objs(*m->m_info, m->possible_max_rank, GFP_NOFS);
+	if (!m->m_info)
+		goto nomem;
+
+	/* pick out active nodes from mds_info (state > 0) */
+	for (i = 0; i < n; i++) {
+		u64 global_id;
+		u32 namelen;
+		s32 mds, inc, state;
+		u8 info_v;
+		void *info_end = NULL;
+		struct ceph_entity_addr addr;
+		u32 num_export_targets;
+		void *pexport_targets = NULL;
+		struct ceph_timespec laggy_since;
+		struct ceph_mds_info *info;
+		bool laggy;
+
+		ceph_decode_need(p, end, sizeof(u64) + 1, bad);
+		global_id = ceph_decode_64(p);
+		info_v= ceph_decode_8(p);
+		if (info_v >= 4) {
+			u32 info_len;
+			ceph_decode_need(p, end, 1 + sizeof(u32), bad);
+			*p += sizeof(u8);	/* info_cv */
+			info_len = ceph_decode_32(p);
+			info_end = *p + info_len;
+			if (info_end > end)
+				goto bad;
+		}
+
+		ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
+		*p += sizeof(u64);
+		namelen = ceph_decode_32(p);  /* skip mds name */
+		*p += namelen;
+
+		ceph_decode_32_safe(p, end, mds, bad);
+		ceph_decode_32_safe(p, end, inc, bad);
+		ceph_decode_32_safe(p, end, state, bad);
+		*p += sizeof(u64);		/* state_seq */
+		if (info_v >= 8)
+			err = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
+		else
+			err = ceph_decode_entity_addr(p, end, &addr);
+		if (err)
+			goto corrupt;
+
+		ceph_decode_copy_safe(p, end, &laggy_since, sizeof(laggy_since),
+				      bad);
+		laggy = laggy_since.tv_sec != 0 || laggy_since.tv_nsec != 0;
+		*p += sizeof(u32);
+		ceph_decode_32_safe(p, end, namelen, bad);
+		*p += namelen;
+		if (info_v >= 2) {
+			ceph_decode_32_safe(p, end, num_export_targets, bad);
+			pexport_targets = *p;
+			*p += num_export_targets * sizeof(u32);
+		} else {
+			num_export_targets = 0;
+		}
+
+		if (info_end && *p != info_end) {
+			if (*p > info_end)
+				goto bad;
+			*p = info_end;
+		}
+
+		doutc(cl, "%d/%d %lld mds%d.%d %s %s%s\n", i+1, n, global_id,
+		      mds, inc, ceph_pr_addr(&addr),
+		      ceph_mds_state_name(state), laggy ? "(laggy)" : "");
+
+		if (mds < 0 || mds >= m->possible_max_rank) {
+			pr_warn_client(cl, "got incorrect mds(%d)\n", mds);
+			continue;
+		}
+
+		if (state <= 0) {
+			doutc(cl, "got incorrect state(%s)\n",
+			      ceph_mds_state_name(state));
+			continue;
+		}
+
+		info = &m->m_info[mds];
+		info->global_id = global_id;
+		info->state = state;
+		info->addr = addr;
+		info->laggy = laggy;
+		info->num_export_targets = num_export_targets;
+		if (num_export_targets) {
+			info->export_targets = kcalloc(num_export_targets,
+						       sizeof(u32), GFP_NOFS);
+			if (!info->export_targets)
+				goto nomem;
+			for (j = 0; j < num_export_targets; j++) {
+				target = ceph_decode_32(&pexport_targets);
+				info->export_targets[j] = target;
+			}
+		} else {
+			info->export_targets = NULL;
+		}
+	}
+
+	/* pg_pools */
+	ceph_decode_32_safe(p, end, n, bad);
+	m->m_num_data_pg_pools = n;
+	m->m_data_pg_pools = kcalloc(n, sizeof(u64), GFP_NOFS);
+	if (!m->m_data_pg_pools)
+		goto nomem;
+	ceph_decode_need(p, end, sizeof(u64)*(n+1), bad);
+	for (i = 0; i < n; i++)
+		m->m_data_pg_pools[i] = ceph_decode_64(p);
+	m->m_cas_pg_pool = ceph_decode_64(p);
+	m->m_enabled = m->m_epoch > 1;
+
+	mdsmap_ev = 1;
+	if (mdsmap_v >= 2) {
+		ceph_decode_16_safe(p, end, mdsmap_ev, bad_ext);
+	}
+	if (mdsmap_ev >= 3) {
+		if (__decode_and_drop_compat_set(p, end) < 0)
+			goto bad_ext;
+	}
+	/* metadata_pool */
+	if (mdsmap_ev < 5) {
+		__decode_and_drop_type(p, end, u32, bad_ext);
+	} else {
+		__decode_and_drop_type(p, end, u64, bad_ext);
+	}
+
+	/* created + modified + tableserver */
+	__decode_and_drop_type(p, end, struct ceph_timespec, bad_ext);
+	__decode_and_drop_type(p, end, struct ceph_timespec, bad_ext);
+	__decode_and_drop_type(p, end, u32, bad_ext);
+
+	/* in */
+	{
+		int num_laggy = 0;
+		ceph_decode_32_safe(p, end, n, bad_ext);
+		ceph_decode_need(p, end, sizeof(u32) * n, bad_ext);
+
+		for (i = 0; i < n; i++) {
+			s32 mds = ceph_decode_32(p);
+			if (mds >= 0 && mds < m->possible_max_rank) {
+				if (m->m_info[mds].laggy)
+					num_laggy++;
+			}
+		}
+		m->m_num_laggy = num_laggy;
+
+		if (n > m->possible_max_rank) {
+			void *new_m_info = krealloc(m->m_info,
+						    n * sizeof(*m->m_info),
+						    GFP_NOFS | __GFP_ZERO);
+			if (!new_m_info)
+				goto nomem;
+			m->m_info = new_m_info;
+		}
+		m->possible_max_rank = n;
+	}
+
+	/* inc */
+	__decode_and_drop_map(p, end, u32, u32, bad_ext);
+	/* up */
+	__decode_and_drop_map(p, end, u32, u64, bad_ext);
+	/* failed */
+	__decode_and_drop_set(p, end, u32, bad_ext);
+	/* stopped */
+	__decode_and_drop_set(p, end, u32, bad_ext);
+
+	if (mdsmap_ev >= 4) {
+		/* last_failure_osd_epoch */
+		__decode_and_drop_type(p, end, u32, bad_ext);
+	}
+	if (mdsmap_ev >= 6) {
+		/* ever_allowed_snaps */
+		__decode_and_drop_type(p, end, u8, bad_ext);
+		/* explicitly_allowed_snaps */
+		__decode_and_drop_type(p, end, u8, bad_ext);
+	}
+	if (mdsmap_ev >= 7) {
+		/* inline_data_enabled */
+		__decode_and_drop_type(p, end, u8, bad_ext);
+	}
+	if (mdsmap_ev >= 8) {
+		size_t fsname_len;
+
+		/* enabled */
+		ceph_decode_8_safe(p, end, m->m_enabled, bad_ext);
+
+		/* fs_name */
+		m->m_fs_name = ceph_extract_encoded_string(p, end,
+							   &fsname_len,
+							   GFP_NOFS);
+		if (IS_ERR(m->m_fs_name)) {
+			m->m_fs_name = NULL;
+			goto nomem;
+		}
+
+		/* validate fsname against mds_namespace */
+		if (!namespace_equals(mdsc->fsc->mount_options, m->m_fs_name,
+				      fsname_len)) {
+			pr_warn_client(cl, "fsname %s doesn't match mds_namespace %s\n",
+				       m->m_fs_name,
+				       mdsc->fsc->mount_options->mds_namespace);
+			goto bad;
+		}
+	} else {
+		m->m_enabled = false;
+		m->m_fs_name = kstrdup(CEPH_OLD_FS_NAME, GFP_NOFS);
+		if (!m->m_fs_name)
+			goto nomem;
+	}
+	/* damaged */
+	if (mdsmap_ev >= 9) {
+		size_t need;
+		ceph_decode_32_safe(p, end, n, bad_ext);
+		need = sizeof(u32) * n;
+		ceph_decode_need(p, end, need, bad_ext);
+		*p += need;
+		m->m_damaged = n > 0;
+	} else {
+		m->m_damaged = false;
+	}
+	if (mdsmap_ev >= 17) {
+		/* balancer */
+		ceph_decode_skip_string(p, end, bad_ext);
+		/* standby_count_wanted */
+		ceph_decode_skip_32(p, end, bad_ext);
+		/* old_max_mds */
+		ceph_decode_skip_32(p, end, bad_ext);
+		/* min_compat_client */
+		ceph_decode_skip_8(p, end, bad_ext);
+		/* required_client_features */
+		ceph_decode_skip_set(p, end, 64, bad_ext);
+		/* bal_rank_mask */
+		ceph_decode_skip_string(p, end, bad_ext);
+	}
+	if (mdsmap_ev >= 18) {
+		ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext);
+	}
+bad_ext:
+	doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
+	      !!m->m_enabled, !!m->m_damaged, m->m_num_laggy);
+	*p = end;
+	doutc(cl, "success epoch %u\n", m->m_epoch);
+	return m;
+nomem:
+	err = -ENOMEM;
+	goto out_err;
+corrupt:
+	pr_err_client(cl, "corrupt mdsmap\n");
+	print_hex_dump(KERN_DEBUG, "mdsmap: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       start, end - start, true);
+out_err:
+	ceph_mdsmap_destroy(m);
+	return ERR_PTR(err);
+bad:
+	err = -EINVAL;
+	goto corrupt;
+}
+
+void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
+{
+	int i;
+
+	if (m->m_info) {
+		for (i = 0; i < m->possible_max_rank; i++)
+			kfree(m->m_info[i].export_targets);
+		kfree(m->m_info);
+	}
+	kfree(m->m_data_pg_pools);
+	kfree(m->m_fs_name);
+	kfree(m);
+}
+
+bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m)
+{
+	int i, nr_active = 0;
+	if (!m->m_enabled)
+		return false;
+	if (m->m_damaged)
+		return false;
+	if (m->m_num_laggy == m->m_num_active_mds)
+		return false;
+	for (i = 0; i < m->possible_max_rank; i++) {
+		if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE)
+			nr_active++;
+	}
+	return nr_active > 0;
+}

linux-7.2.3/fs/ceph/mdsmap.h

@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_MDSMAP_H
+#define _FS_CEPH_MDSMAP_H
+
+#include <linux/bug.h>
+#include <linux/ceph/types.h>
+
+struct ceph_mds_client;
+
+/*
+ * mds map - describe servers in the mds cluster.
+ *
+ * we limit fields to those the client actually xcares about
+ */
+struct ceph_mds_info {
+	u64 global_id;
+	struct ceph_entity_addr addr;
+	s32 state;
+	int num_export_targets;
+	bool laggy;
+	u32 *export_targets;
+};
+
+struct ceph_mdsmap {
+	u32 m_epoch, m_client_epoch, m_last_failure;
+	u32 m_root;
+	u32 m_session_timeout;          /* seconds */
+	u32 m_session_autoclose;        /* seconds */
+	u64 m_max_file_size;
+	/*
+	 * maximum size for xattrs blob.
+	 * Zeroed by default to force the usage of the (sync) SETXATTR Op.
+	 */
+	u64 m_max_xattr_size;
+	u32 m_max_mds;			/* expected up:active mds number */
+	u32 m_num_active_mds;		/* actual up:active mds number */
+	u32 possible_max_rank;		/* possible max rank index */
+	struct ceph_mds_info *m_info;
+
+	/* which object pools file data can be stored in */
+	int m_num_data_pg_pools;
+	u64 *m_data_pg_pools;
+	u64 m_cas_pg_pool;
+
+	bool m_enabled;
+	bool m_damaged;
+	int m_num_laggy;
+	char *m_fs_name;
+};
+
+static inline struct ceph_entity_addr *
+ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
+{
+	if (w >= m->possible_max_rank)
+		return NULL;
+	return &m->m_info[w].addr;
+}
+
+static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
+{
+	BUG_ON(w < 0);
+	if (w >= m->possible_max_rank)
+		return CEPH_MDS_STATE_DNE;
+	return m->m_info[w].state;
+}
+
+static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
+{
+	if (w >= 0 && w < m->possible_max_rank)
+		return m->m_info[w].laggy;
+	return false;
+}
+
+extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
+struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
+				       void *end, bool msgr2);
+extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
+extern bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m);
+
+#endif

linux-7.2.3/fs/ceph/metric.c

@@ -0,0 +1,533 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/math64.h>
+#include <linux/ratelimit.h>
+
+#include <linux/ceph/decode.h>
+
+#include "metric.h"
+#include "mds_client.h"
+
+static bool metrics_disable_warned;
+
+static inline u32 ceph_subvolume_entry_payload_len(void)
+{
+	return sizeof(struct ceph_subvolume_metric_entry_wire);
+}
+
+static inline u32 ceph_subvolume_entry_encoded_len(void)
+{
+	return CEPH_ENCODING_START_BLK_LEN +
+		ceph_subvolume_entry_payload_len();
+}
+
+static inline u32 ceph_subvolume_outer_payload_len(u32 nr_subvols)
+{
+	/* count is encoded as le64 (size_t on wire) to match FUSE client */
+	return sizeof(__le64) +
+		nr_subvols * ceph_subvolume_entry_encoded_len();
+}
+
+static inline u32 ceph_subvolume_metric_data_len(u32 nr_subvols)
+{
+	return CEPH_ENCODING_START_BLK_LEN +
+		ceph_subvolume_outer_payload_len(nr_subvols);
+}
+
+static inline u32 ceph_subvolume_clamp_u32(u64 val)
+{
+	return val > U32_MAX ? U32_MAX : (u32)val;
+}
+
+static void ceph_init_subvolume_wire_entry(
+	struct ceph_subvolume_metric_entry_wire *dst,
+	const struct ceph_subvol_metric_snapshot *src)
+{
+	dst->subvolume_id = cpu_to_le64(src->subvolume_id);
+	dst->read_ops = cpu_to_le32(ceph_subvolume_clamp_u32(src->read_ops));
+	dst->write_ops = cpu_to_le32(ceph_subvolume_clamp_u32(src->write_ops));
+	dst->read_bytes = cpu_to_le64(src->read_bytes);
+	dst->write_bytes = cpu_to_le64(src->write_bytes);
+	dst->read_latency_us = cpu_to_le64(src->read_latency_us);
+	dst->write_latency_us = cpu_to_le64(src->write_latency_us);
+	dst->time_stamp = 0;
+}
+
+static int ceph_encode_subvolume_metrics(void **p, void *end,
+					 struct ceph_subvol_metric_snapshot *subvols,
+					 u32 nr_subvols)
+{
+	u32 i;
+
+	ceph_start_encoding(p, 1, 1,
+			    ceph_subvolume_outer_payload_len(nr_subvols));
+	/* count is encoded as le64 (size_t on wire) to match FUSE client */
+	ceph_encode_64_safe(p, end, (u64)nr_subvols, enc_err);
+
+	for (i = 0; i < nr_subvols; i++) {
+		struct ceph_subvolume_metric_entry_wire wire_entry;
+
+		ceph_init_subvolume_wire_entry(&wire_entry, &subvols[i]);
+		ceph_start_encoding(p, 1, 1,
+				    ceph_subvolume_entry_payload_len());
+		ceph_encode_copy_safe(p, end, &wire_entry,
+				      sizeof(wire_entry), enc_err);
+	}
+
+	return 0;
+enc_err:
+	return -ERANGE;
+}
+
+static void ktime_to_ceph_timespec(struct ceph_timespec *ts, ktime_t val)
+{
+	struct timespec64 t = ktime_to_timespec64(val);
+	ceph_encode_timespec64(ts, &t);
+}
+
+static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *s)
+{
+	struct ceph_metric_head *head;
+	struct ceph_metric_cap *cap;
+	struct ceph_metric_read_latency *read;
+	struct ceph_metric_write_latency *write;
+	struct ceph_metric_metadata_latency *meta;
+	struct ceph_metric_dlease *dlease;
+	struct ceph_opened_files *files;
+	struct ceph_pinned_icaps *icaps;
+	struct ceph_opened_inodes *inodes;
+	struct ceph_read_io_size *rsize;
+	struct ceph_write_io_size *wsize;
+	struct ceph_client_metric *m = &mdsc->metric;
+	struct ceph_subvol_metric_snapshot *subvols = NULL;
+	u64 nr_caps = atomic64_read(&m->total_caps);
+	u32 header_len = sizeof(struct ceph_metric_header);
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_msg *msg;
+	u32 nr_subvols = 0;
+	size_t subvol_len = 0;
+	void *cursor;
+	s64 sum;
+	s32 items = 0;
+	s32 len;
+
+	/* Do not send the metrics until the MDS rank is ready */
+	mutex_lock(&mdsc->mutex);
+	if (ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) != CEPH_MDS_STATE_ACTIVE) {
+		mutex_unlock(&mdsc->mutex);
+		return false;
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	if (ceph_subvolume_metrics_enabled(&mdsc->subvol_metrics) &&
+	    test_bit(CEPHFS_FEATURE_SUBVOLUME_METRICS, &s->s_features)) {
+		int ret;
+
+		ret = ceph_subvolume_metrics_snapshot(&mdsc->subvol_metrics,
+						      &subvols, &nr_subvols,
+						      true);
+		if (ret) {
+			pr_warn_client(cl, "failed to snapshot subvolume metrics: %d\n",
+				       ret);
+			/*
+			 * On error, ceph_subvolume_metrics_snapshot() guarantees
+			 * *out = NULL and *nr = 0 at function entry, so subvols
+			 * is already NULL here - no cleanup needed.
+			 */
+			nr_subvols = 0;
+			subvols = NULL;
+		}
+	}
+
+	if (nr_subvols) {
+		/* type (le32) + ENCODE_START payload - no metric header */
+		subvol_len = sizeof(__le32) +
+			     ceph_subvolume_metric_data_len(nr_subvols);
+	}
+
+	len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
+	      + sizeof(*meta) + sizeof(*dlease) + sizeof(*files)
+	      + sizeof(*icaps) + sizeof(*inodes) + sizeof(*rsize)
+	      + sizeof(*wsize) + subvol_len;
+
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
+	if (!msg) {
+		pr_err_client(cl, "to mds%d, failed to allocate message\n",
+			      s->s_mds);
+		kfree(subvols);
+		return false;
+	}
+
+	head = msg->front.iov_base;
+
+	/* encode the cap metric */
+	cap = (struct ceph_metric_cap *)(head + 1);
+	cap->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO);
+	cap->header.ver = 1;
+	cap->header.compat = 1;
+	cap->header.data_len = cpu_to_le32(sizeof(*cap) - header_len);
+	cap->hit = cpu_to_le64(percpu_counter_sum(&m->i_caps_hit));
+	cap->mis = cpu_to_le64(percpu_counter_sum(&m->i_caps_mis));
+	cap->total = cpu_to_le64(nr_caps);
+	items++;
+
+	/* encode the read latency metric */
+	read = (struct ceph_metric_read_latency *)(cap + 1);
+	read->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY);
+	read->header.ver = 2;
+	read->header.compat = 1;
+	read->header.data_len = cpu_to_le32(sizeof(*read) - header_len);
+	sum = m->metric[METRIC_READ].latency_sum;
+	ktime_to_ceph_timespec(&read->lat, sum);
+	ktime_to_ceph_timespec(&read->avg, m->metric[METRIC_READ].latency_avg);
+	read->sq_sum = cpu_to_le64(m->metric[METRIC_READ].latency_sq_sum);
+	read->count = cpu_to_le64(m->metric[METRIC_READ].total);
+	items++;
+
+	/* encode the write latency metric */
+	write = (struct ceph_metric_write_latency *)(read + 1);
+	write->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY);
+	write->header.ver = 2;
+	write->header.compat = 1;
+	write->header.data_len = cpu_to_le32(sizeof(*write) - header_len);
+	sum = m->metric[METRIC_WRITE].latency_sum;
+	ktime_to_ceph_timespec(&write->lat, sum);
+	ktime_to_ceph_timespec(&write->avg, m->metric[METRIC_WRITE].latency_avg);
+	write->sq_sum = cpu_to_le64(m->metric[METRIC_WRITE].latency_sq_sum);
+	write->count = cpu_to_le64(m->metric[METRIC_WRITE].total);
+	items++;
+
+	/* encode the metadata latency metric */
+	meta = (struct ceph_metric_metadata_latency *)(write + 1);
+	meta->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY);
+	meta->header.ver = 2;
+	meta->header.compat = 1;
+	meta->header.data_len = cpu_to_le32(sizeof(*meta) - header_len);
+	sum = m->metric[METRIC_METADATA].latency_sum;
+	ktime_to_ceph_timespec(&meta->lat, sum);
+	ktime_to_ceph_timespec(&meta->avg, m->metric[METRIC_METADATA].latency_avg);
+	meta->sq_sum = cpu_to_le64(m->metric[METRIC_METADATA].latency_sq_sum);
+	meta->count = cpu_to_le64(m->metric[METRIC_METADATA].total);
+	items++;
+
+	/* encode the dentry lease metric */
+	dlease = (struct ceph_metric_dlease *)(meta + 1);
+	dlease->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_DENTRY_LEASE);
+	dlease->header.ver = 1;
+	dlease->header.compat = 1;
+	dlease->header.data_len = cpu_to_le32(sizeof(*dlease) - header_len);
+	dlease->hit = cpu_to_le64(percpu_counter_sum(&m->d_lease_hit));
+	dlease->mis = cpu_to_le64(percpu_counter_sum(&m->d_lease_mis));
+	dlease->total = cpu_to_le64(atomic64_read(&m->total_dentries));
+	items++;
+
+	sum = percpu_counter_sum(&m->total_inodes);
+
+	/* encode the opened files metric */
+	files = (struct ceph_opened_files *)(dlease + 1);
+	files->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_OPENED_FILES);
+	files->header.ver = 1;
+	files->header.compat = 1;
+	files->header.data_len = cpu_to_le32(sizeof(*files) - header_len);
+	files->opened_files = cpu_to_le64(atomic64_read(&m->opened_files));
+	files->total = cpu_to_le64(sum);
+	items++;
+
+	/* encode the pinned icaps metric */
+	icaps = (struct ceph_pinned_icaps *)(files + 1);
+	icaps->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_PINNED_ICAPS);
+	icaps->header.ver = 1;
+	icaps->header.compat = 1;
+	icaps->header.data_len = cpu_to_le32(sizeof(*icaps) - header_len);
+	icaps->pinned_icaps = cpu_to_le64(nr_caps);
+	icaps->total = cpu_to_le64(sum);
+	items++;
+
+	/* encode the opened inodes metric */
+	inodes = (struct ceph_opened_inodes *)(icaps + 1);
+	inodes->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_OPENED_INODES);
+	inodes->header.ver = 1;
+	inodes->header.compat = 1;
+	inodes->header.data_len = cpu_to_le32(sizeof(*inodes) - header_len);
+	inodes->opened_inodes = cpu_to_le64(percpu_counter_sum(&m->opened_inodes));
+	inodes->total = cpu_to_le64(sum);
+	items++;
+
+	/* encode the read io size metric */
+	rsize = (struct ceph_read_io_size *)(inodes + 1);
+	rsize->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_IO_SIZES);
+	rsize->header.ver = 1;
+	rsize->header.compat = 1;
+	rsize->header.data_len = cpu_to_le32(sizeof(*rsize) - header_len);
+	rsize->total_ops = cpu_to_le64(m->metric[METRIC_READ].total);
+	rsize->total_size = cpu_to_le64(m->metric[METRIC_READ].size_sum);
+	items++;
+
+	/* encode the write io size metric */
+	wsize = (struct ceph_write_io_size *)(rsize + 1);
+	wsize->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_IO_SIZES);
+	wsize->header.ver = 1;
+	wsize->header.compat = 1;
+	wsize->header.data_len = cpu_to_le32(sizeof(*wsize) - header_len);
+	wsize->total_ops = cpu_to_le64(m->metric[METRIC_WRITE].total);
+	wsize->total_size = cpu_to_le64(m->metric[METRIC_WRITE].size_sum);
+	items++;
+
+	cursor = wsize + 1;
+
+	if (nr_subvols) {
+		void *payload;
+		void *payload_end;
+		int ret;
+
+		/* Emit only the type (le32), no ver/compat/data_len */
+		ceph_encode_32(&cursor, CLIENT_METRIC_TYPE_SUBVOLUME_METRICS);
+		items++;
+
+		payload = cursor;
+		payload_end = (char *)payload +
+			      ceph_subvolume_metric_data_len(nr_subvols);
+
+		ret = ceph_encode_subvolume_metrics(&payload, payload_end,
+						    subvols, nr_subvols);
+		if (ret) {
+			pr_warn_client(cl,
+				       "failed to encode subvolume metrics\n");
+			kfree(subvols);
+			ceph_msg_put(msg);
+			return false;
+		}
+
+		WARN_ON(payload != payload_end);
+		cursor = payload;
+	}
+
+	put_unaligned_le32(items, &head->num);
+	msg->front.iov_len = (char *)cursor - (char *)head;
+	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);
+
+	ceph_con_send(&s->s_con, msg);
+
+	if (nr_subvols) {
+		mutex_lock(&mdsc->subvol_metrics_last_mutex);
+		kfree(mdsc->subvol_metrics_last);
+		mdsc->subvol_metrics_last = subvols;
+		mdsc->subvol_metrics_last_nr = nr_subvols;
+		mdsc->subvol_metrics_sent += nr_subvols;
+		mdsc->subvol_metrics_nonzero_sends++;
+		mutex_unlock(&mdsc->subvol_metrics_last_mutex);
+
+		subvols = NULL;
+	}
+	kfree(subvols);
+
+	return true;
+}
+
+
+static void metric_get_session(struct ceph_mds_client *mdsc)
+{
+	struct ceph_mds_session *s;
+	int i;
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!s)
+			continue;
+
+		/*
+		 * Skip it if MDS doesn't support the metric collection,
+		 * or the MDS will close the session's socket connection
+		 * directly when it get this message.
+		 *
+		 * Also skip sessions that don't support SUBVOLUME_METRICS
+		 * when subvolume metrics collection is enabled. This ensures
+		 * we only send subvolume metrics to MDSs that understand them.
+		 * If no session supports the feature, metrics won't be sent.
+		 */
+		if (check_session_state(s) &&
+		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
+			if (ceph_subvolume_metrics_enabled(&mdsc->subvol_metrics) &&
+			    !test_bit(CEPHFS_FEATURE_SUBVOLUME_METRICS,
+				      &s->s_features)) {
+				ceph_put_mds_session(s);
+				continue;
+			}
+			mdsc->metric.session = s;
+			break;
+		}
+
+		ceph_put_mds_session(s);
+	}
+	mutex_unlock(&mdsc->mutex);
+}
+
+static void metric_delayed_work(struct work_struct *work)
+{
+	struct ceph_client_metric *m =
+		container_of(work, struct ceph_client_metric, delayed_work.work);
+	struct ceph_mds_client *mdsc =
+		container_of(m, struct ceph_mds_client, metric);
+
+	if (mdsc->stopping)
+		return;
+
+	if (disable_send_metrics) {
+		if (!metrics_disable_warned) {
+			pr_info("ceph: metrics sending disabled via module parameter\n");
+			metrics_disable_warned = true;
+		}
+		return;
+	}
+	metrics_disable_warned = false;
+
+	if (!m->session || !check_session_state(m->session)) {
+		if (m->session) {
+			ceph_put_mds_session(m->session);
+			m->session = NULL;
+		}
+		metric_get_session(mdsc);
+	}
+
+	if (m->session)
+		ceph_mdsc_send_metrics(mdsc, m->session);
+	else
+		pr_warn_ratelimited("ceph: metrics worker has no MDS session\n");
+
+	metric_schedule_delayed(m);
+}
+
+int ceph_metric_init(struct ceph_client_metric *m)
+{
+	struct ceph_metric *metric;
+	int ret, i;
+
+	if (!m)
+		return -EINVAL;
+
+	atomic64_set(&m->total_dentries, 0);
+	ret = percpu_counter_init(&m->d_lease_hit, 0, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	ret = percpu_counter_init(&m->d_lease_mis, 0, GFP_KERNEL);
+	if (ret)
+		goto err_d_lease_mis;
+
+	atomic64_set(&m->total_caps, 0);
+	ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL);
+	if (ret)
+		goto err_i_caps_hit;
+
+	ret = percpu_counter_init(&m->i_caps_mis, 0, GFP_KERNEL);
+	if (ret)
+		goto err_i_caps_mis;
+
+	for (i = 0; i < METRIC_MAX; i++) {
+		metric = &m->metric[i];
+		spin_lock_init(&metric->lock);
+		metric->size_sum = 0;
+		metric->size_min = U64_MAX;
+		metric->size_max = 0;
+		metric->total = 0;
+		metric->latency_sum = 0;
+		metric->latency_avg = 0;
+		metric->latency_sq_sum = 0;
+		metric->latency_min = KTIME_MAX;
+		metric->latency_max = 0;
+	}
+
+	atomic64_set(&m->opened_files, 0);
+	ret = percpu_counter_init(&m->opened_inodes, 0, GFP_KERNEL);
+	if (ret)
+		goto err_opened_inodes;
+	ret = percpu_counter_init(&m->total_inodes, 0, GFP_KERNEL);
+	if (ret)
+		goto err_total_inodes;
+
+	m->session = NULL;
+	INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work);
+
+	return 0;
+
+err_total_inodes:
+	percpu_counter_destroy(&m->opened_inodes);
+err_opened_inodes:
+	percpu_counter_destroy(&m->i_caps_mis);
+err_i_caps_mis:
+	percpu_counter_destroy(&m->i_caps_hit);
+err_i_caps_hit:
+	percpu_counter_destroy(&m->d_lease_mis);
+err_d_lease_mis:
+	percpu_counter_destroy(&m->d_lease_hit);
+
+	return ret;
+}
+
+void ceph_metric_destroy(struct ceph_client_metric *m)
+{
+	if (!m)
+		return;
+
+	cancel_delayed_work_sync(&m->delayed_work);
+
+	percpu_counter_destroy(&m->total_inodes);
+	percpu_counter_destroy(&m->opened_inodes);
+	percpu_counter_destroy(&m->i_caps_mis);
+	percpu_counter_destroy(&m->i_caps_hit);
+	percpu_counter_destroy(&m->d_lease_mis);
+	percpu_counter_destroy(&m->d_lease_hit);
+
+	ceph_put_mds_session(m->session);
+}
+
+#define METRIC_UPDATE_MIN_MAX(min, max, new)	\
+{						\
+	if (unlikely(new < min))		\
+		min = new;			\
+	if (unlikely(new > max))		\
+		max = new;			\
+}
+
+static inline void __update_mean_and_stdev(ktime_t total, ktime_t *lavg,
+					   ktime_t *sq_sump, ktime_t lat)
+{
+	ktime_t avg;
+
+	if (unlikely(total == 1)) {
+		*lavg = lat;
+	} else {
+		/* the sq is (lat - old_avg) * (lat - new_avg) */
+		avg = *lavg + div64_s64(lat - *lavg, total);
+		*sq_sump += (lat - *lavg)*(lat - avg);
+		*lavg = avg;
+	}
+}
+
+void ceph_update_metrics(struct ceph_metric *m,
+			 ktime_t r_start, ktime_t r_end,
+			 unsigned int size, int rc)
+{
+	ktime_t lat = ktime_sub(r_end, r_start);
+	ktime_t total;
+
+	if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT))
+		return;
+
+	spin_lock(&m->lock);
+	total = ++m->total;
+	m->size_sum += size;
+	METRIC_UPDATE_MIN_MAX(m->size_min, m->size_max, size);
+	m->latency_sum += lat;
+	METRIC_UPDATE_MIN_MAX(m->latency_min, m->latency_max, lat);
+	__update_mean_and_stdev(total, &m->latency_avg,	&m->latency_sq_sum,
+				lat);
+	spin_unlock(&m->lock);
+}

linux-7.2.3/fs/ceph/metric.h

@@ -0,0 +1,281 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_MDS_METRIC_H
+#define _FS_CEPH_MDS_METRIC_H
+
+#include <linux/ceph/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/ktime.h>
+
+extern bool disable_send_metrics;
+
+enum ceph_metric_type {
+	CLIENT_METRIC_TYPE_CAP_INFO,
+	CLIENT_METRIC_TYPE_READ_LATENCY,
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,
+	CLIENT_METRIC_TYPE_DENTRY_LEASE,
+	CLIENT_METRIC_TYPE_OPENED_FILES,
+	CLIENT_METRIC_TYPE_PINNED_ICAPS,
+	CLIENT_METRIC_TYPE_OPENED_INODES,
+	CLIENT_METRIC_TYPE_READ_IO_SIZES,
+	CLIENT_METRIC_TYPE_WRITE_IO_SIZES,
+	CLIENT_METRIC_TYPE_AVG_READ_LATENCY,
+	CLIENT_METRIC_TYPE_STDEV_READ_LATENCY,
+	CLIENT_METRIC_TYPE_AVG_WRITE_LATENCY,
+	CLIENT_METRIC_TYPE_STDEV_WRITE_LATENCY,
+	CLIENT_METRIC_TYPE_AVG_METADATA_LATENCY,
+	CLIENT_METRIC_TYPE_STDEV_METADATA_LATENCY,
+	CLIENT_METRIC_TYPE_SUBVOLUME_METRICS,
+
+	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_SUBVOLUME_METRICS,
+};
+
+/*
+ * This will always have the highest metric bit value
+ * as the last element of the array.
+ */
+#define CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED {	   \
+	CLIENT_METRIC_TYPE_CAP_INFO,		   \
+	CLIENT_METRIC_TYPE_READ_LATENCY,	   \
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,	   \
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,	   \
+	CLIENT_METRIC_TYPE_DENTRY_LEASE,	   \
+	CLIENT_METRIC_TYPE_OPENED_FILES,	   \
+	CLIENT_METRIC_TYPE_PINNED_ICAPS,	   \
+	CLIENT_METRIC_TYPE_OPENED_INODES,	   \
+	CLIENT_METRIC_TYPE_READ_IO_SIZES,	   \
+	CLIENT_METRIC_TYPE_WRITE_IO_SIZES,	   \
+	CLIENT_METRIC_TYPE_AVG_READ_LATENCY,	   \
+	CLIENT_METRIC_TYPE_STDEV_READ_LATENCY,	   \
+	CLIENT_METRIC_TYPE_AVG_WRITE_LATENCY,	   \
+	CLIENT_METRIC_TYPE_STDEV_WRITE_LATENCY,	   \
+	CLIENT_METRIC_TYPE_AVG_METADATA_LATENCY,   \
+	CLIENT_METRIC_TYPE_STDEV_METADATA_LATENCY, \
+	CLIENT_METRIC_TYPE_SUBVOLUME_METRICS,	   \
+						   \
+	CLIENT_METRIC_TYPE_MAX,			   \
+}
+
+struct ceph_metric_header {
+	__le32 type;     /* ceph metric type */
+	__u8  ver;
+	__u8  compat;
+	__le32 data_len; /* length of sizeof(hit + mis + total) */
+} __packed;
+
+/* metric caps header */
+struct ceph_metric_cap {
+	struct ceph_metric_header header;
+	__le64 hit;
+	__le64 mis;
+	__le64 total;
+} __packed;
+
+/* metric read latency header */
+struct ceph_metric_read_latency {
+	struct ceph_metric_header header;
+	struct ceph_timespec lat;
+	struct ceph_timespec avg;
+	__le64 sq_sum;
+	__le64 count;
+} __packed;
+
+/* metric write latency header */
+struct ceph_metric_write_latency {
+	struct ceph_metric_header header;
+	struct ceph_timespec lat;
+	struct ceph_timespec avg;
+	__le64 sq_sum;
+	__le64 count;
+} __packed;
+
+/* metric metadata latency header */
+struct ceph_metric_metadata_latency {
+	struct ceph_metric_header header;
+	struct ceph_timespec lat;
+	struct ceph_timespec avg;
+	__le64 sq_sum;
+	__le64 count;
+} __packed;
+
+/* metric dentry lease header */
+struct ceph_metric_dlease {
+	struct ceph_metric_header header;
+	__le64 hit;
+	__le64 mis;
+	__le64 total;
+} __packed;
+
+/* metric opened files header */
+struct ceph_opened_files {
+	struct ceph_metric_header header;
+	__le64 opened_files;
+	__le64 total;
+} __packed;
+
+/* metric pinned i_caps header */
+struct ceph_pinned_icaps {
+	struct ceph_metric_header header;
+	__le64 pinned_icaps;
+	__le64 total;
+} __packed;
+
+/* metric opened inodes header */
+struct ceph_opened_inodes {
+	struct ceph_metric_header header;
+	__le64 opened_inodes;
+	__le64 total;
+} __packed;
+
+/* metric read io size header */
+struct ceph_read_io_size {
+	struct ceph_metric_header header;
+	__le64 total_ops;
+	__le64 total_size;
+} __packed;
+
+/* metric write io size header */
+struct ceph_write_io_size {
+	struct ceph_metric_header header;
+	__le64 total_ops;
+	__le64 total_size;
+} __packed;
+
+/**
+ * struct ceph_subvolume_metric_entry_wire - On-wire format sent to MDS
+ * @subvolume_id: Subvolume identifier
+ * @read_ops: Read operation count (32-bit, clamped from 64-bit internal)
+ * @write_ops: Write operation count (32-bit, clamped from 64-bit internal)
+ * @read_bytes: Total bytes read
+ * @write_bytes: Total bytes written
+ * @read_latency_us: Cumulative read latency in microseconds
+ * @write_latency_us: Cumulative write latency in microseconds
+ * @time_stamp: Collection timestamp (currently unused, set to 0)
+ *
+ * Wire format must match C++ AggregatedIOMetrics struct in MDS.
+ */
+struct ceph_subvolume_metric_entry_wire {
+	__le64 subvolume_id;
+	__le32 read_ops;
+	__le32 write_ops;
+	__le64 read_bytes;
+	__le64 write_bytes;
+	__le64 read_latency_us;
+	__le64 write_latency_us;
+	__le64 time_stamp;
+} __packed;
+
+/* Old struct kept for internal tracking, not used on wire */
+struct ceph_subvolume_metric_entry {
+	__le64 subvolume_id;
+	__le64 read_ops;
+	__le64 write_ops;
+	__le64 read_bytes;
+	__le64 write_bytes;
+	__le64 read_latency_us;
+	__le64 write_latency_us;
+} __packed;
+
+struct ceph_metric_head {
+	__le32 num;	/* the number of metrics that will be sent */
+} __packed;
+
+enum metric_type {
+	METRIC_READ,
+	METRIC_WRITE,
+	METRIC_METADATA,
+	METRIC_COPYFROM,
+	METRIC_MAX
+};
+
+struct ceph_metric {
+	spinlock_t lock;
+	u64 total;
+	u64 size_sum;
+	u64 size_min;
+	u64 size_max;
+	ktime_t latency_sum;
+	ktime_t latency_avg;
+	ktime_t latency_sq_sum;
+	ktime_t latency_min;
+	ktime_t latency_max;
+};
+
+/* This is the global metrics */
+struct ceph_client_metric {
+	atomic64_t            total_dentries;
+	struct percpu_counter d_lease_hit;
+	struct percpu_counter d_lease_mis;
+
+	atomic64_t            total_caps;
+	struct percpu_counter i_caps_hit;
+	struct percpu_counter i_caps_mis;
+
+	struct ceph_metric metric[METRIC_MAX];
+
+	/* The total number of directories and files that are opened */
+	atomic64_t opened_files;
+
+	/* The total number of inodes that have opened files or directories */
+	struct percpu_counter opened_inodes;
+	struct percpu_counter total_inodes;
+
+	struct ceph_mds_session *session;
+	struct delayed_work delayed_work;  /* delayed work */
+};
+
+static inline void metric_schedule_delayed(struct ceph_client_metric *m)
+{
+	if (disable_send_metrics)
+		return;
+
+	/* per second */
+	schedule_delayed_work(&m->delayed_work, round_jiffies_relative(HZ));
+}
+
+extern int ceph_metric_init(struct ceph_client_metric *m);
+extern void ceph_metric_destroy(struct ceph_client_metric *m);
+
+static inline void ceph_update_cap_hit(struct ceph_client_metric *m)
+{
+	percpu_counter_inc(&m->i_caps_hit);
+}
+
+static inline void ceph_update_cap_mis(struct ceph_client_metric *m)
+{
+	percpu_counter_inc(&m->i_caps_mis);
+}
+
+extern void ceph_update_metrics(struct ceph_metric *m,
+				ktime_t r_start, ktime_t r_end,
+				unsigned int size, int rc);
+
+static inline void ceph_update_read_metrics(struct ceph_client_metric *m,
+					    ktime_t r_start, ktime_t r_end,
+					    unsigned int size, int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_READ],
+			    r_start, r_end, size, rc);
+}
+static inline void ceph_update_write_metrics(struct ceph_client_metric *m,
+					     ktime_t r_start, ktime_t r_end,
+					     unsigned int size, int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_WRITE],
+			    r_start, r_end, size, rc);
+}
+static inline void ceph_update_metadata_metrics(struct ceph_client_metric *m,
+						ktime_t r_start, ktime_t r_end,
+						int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_METADATA],
+			    r_start, r_end, 0, rc);
+}
+static inline void ceph_update_copyfrom_metrics(struct ceph_client_metric *m,
+						ktime_t r_start, ktime_t r_end,
+						unsigned int size, int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_COPYFROM],
+			    r_start, r_end, size, rc);
+}
+#endif /* _FS_CEPH_MDS_METRIC_H */

linux-7.2.3/fs/ceph/quota.c

@@ -0,0 +1,564 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * quota.c - CephFS quota
+ *
+ * Copyright (C) 2017-2018 SUSE
+ */
+
+#include <linux/statfs.h>
+
+#include "super.h"
+#include "mds_client.h"
+
+void ceph_adjust_quota_realms_count(struct inode *inode, bool inc)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	if (inc)
+		atomic64_inc(&mdsc->quotarealms_count);
+	else
+		atomic64_dec(&mdsc->quotarealms_count);
+}
+
+static inline bool ceph_has_realms_with_quotas(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
+	struct inode *root = d_inode(sb->s_root);
+
+	if (atomic64_read(&mdsc->quotarealms_count) > 0)
+		return true;
+	/* 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;
+}
+
+void ceph_handle_quota(struct ceph_mds_client *mdsc,
+		       struct ceph_mds_session *session,
+		       struct ceph_msg *msg)
+{
+	struct super_block *sb = mdsc->fsc->sb;
+	struct ceph_mds_quota *h = msg->front.iov_base;
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_vino vino;
+	struct inode *inode;
+	struct ceph_inode_info *ci;
+
+	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
+		return;
+
+	if (msg->front.iov_len < sizeof(*h)) {
+		pr_err_client(cl, "corrupt message mds%d len %d\n",
+			      session->s_mds, (int)msg->front.iov_len);
+		ceph_msg_dump(msg);
+		goto out;
+	}
+
+	/* lookup inode */
+	vino.ino = le64_to_cpu(h->ino);
+	vino.snap = CEPH_NOSNAP;
+	inode = ceph_find_inode(sb, vino);
+	if (!inode) {
+		pr_warn_client(cl, "failed to find inode %llx\n", vino.ino);
+		goto out;
+	}
+	ci = ceph_inode(inode);
+
+	spin_lock(&ci->i_ceph_lock);
+	ci->i_rbytes = le64_to_cpu(h->rbytes);
+	ci->i_rfiles = le64_to_cpu(h->rfiles);
+	ci->i_rsubdirs = le64_to_cpu(h->rsubdirs);
+	__ceph_update_quota(ci, le64_to_cpu(h->max_bytes),
+		            le64_to_cpu(h->max_files));
+	spin_unlock(&ci->i_ceph_lock);
+
+	iput(inode);
+out:
+	ceph_dec_mds_stopping_blocker(mdsc);
+}
+
+static struct ceph_quotarealm_inode *
+find_quotarealm_inode(struct ceph_mds_client *mdsc, u64 ino)
+{
+	struct ceph_quotarealm_inode *qri = NULL;
+	struct rb_node **node, *parent = NULL;
+	struct ceph_client *cl = mdsc->fsc->client;
+
+	mutex_lock(&mdsc->quotarealms_inodes_mutex);
+	node = &(mdsc->quotarealms_inodes.rb_node);
+	while (*node) {
+		parent = *node;
+		qri = container_of(*node, struct ceph_quotarealm_inode, node);
+
+		if (ino < qri->ino)
+			node = &((*node)->rb_left);
+		else if (ino > qri->ino)
+			node = &((*node)->rb_right);
+		else
+			break;
+	}
+	if (!qri || (qri->ino != ino)) {
+		/* Not found, create a new one and insert it */
+		qri = kmalloc_obj(*qri);
+		if (qri) {
+			qri->ino = ino;
+			qri->inode = NULL;
+			qri->timeout = 0;
+			mutex_init(&qri->mutex);
+			rb_link_node(&qri->node, parent, node);
+			rb_insert_color(&qri->node, &mdsc->quotarealms_inodes);
+		} else
+			pr_warn_client(cl, "Failed to alloc quotarealms_inode\n");
+	}
+	mutex_unlock(&mdsc->quotarealms_inodes_mutex);
+
+	return qri;
+}
+
+/*
+ * This function will try to lookup a realm inode which isn't visible in the
+ * filesystem mountpoint.  A list of these kind of inodes (not visible) is
+ * maintained in the mdsc and freed only when the filesystem is umounted.
+ *
+ * Note that these inodes are kept in this list even if the lookup fails, which
+ * allows to prevent useless lookup requests.
+ */
+static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
+					     struct super_block *sb,
+					     struct ceph_snap_realm *realm)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_quotarealm_inode *qri;
+	struct inode *in;
+
+	qri = find_quotarealm_inode(mdsc, realm->ino);
+	if (!qri)
+		return NULL;
+
+	mutex_lock(&qri->mutex);
+	if (qri->inode && ceph_is_any_caps(qri->inode)) {
+		/* A request has already returned the inode */
+		mutex_unlock(&qri->mutex);
+		return qri->inode;
+	}
+	/* Check if this inode lookup has failed recently */
+	if (qri->timeout &&
+	    time_before_eq(jiffies, qri->timeout)) {
+		mutex_unlock(&qri->mutex);
+		return NULL;
+	}
+	if (qri->inode) {
+		/* get caps */
+		int ret = __ceph_do_getattr(qri->inode, NULL,
+					    CEPH_STAT_CAP_INODE, true);
+		if (ret >= 0)
+			in = qri->inode;
+		else
+			in = ERR_PTR(ret);
+	}  else {
+		in = ceph_lookup_inode(sb, realm->ino);
+	}
+
+	if (IS_ERR(in)) {
+		doutc(cl, "Can't lookup inode %llx (err: %ld)\n", realm->ino,
+		      PTR_ERR(in));
+		qri->timeout = jiffies + secs_to_jiffies(60); /* XXX */
+	} else {
+		qri->timeout = 0;
+		qri->inode = in;
+	}
+	mutex_unlock(&qri->mutex);
+
+	return in;
+}
+
+void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
+{
+	struct ceph_quotarealm_inode *qri;
+	struct rb_node *node;
+
+	/*
+	 * It should now be safe to clean quotarealms_inode tree without holding
+	 * mdsc->quotarealms_inodes_mutex...
+	 */
+	mutex_lock(&mdsc->quotarealms_inodes_mutex);
+	while (!RB_EMPTY_ROOT(&mdsc->quotarealms_inodes)) {
+		node = rb_first(&mdsc->quotarealms_inodes);
+		qri = rb_entry(node, struct ceph_quotarealm_inode, node);
+		rb_erase(node, &mdsc->quotarealms_inodes);
+		iput(qri->inode);
+		kfree(qri);
+	}
+	mutex_unlock(&mdsc->quotarealms_inodes_mutex);
+}
+
+/*
+ * This function walks through the snaprealm for an inode and set the
+ * realmp with the first snaprealm that has quotas set (max_files,
+ * max_bytes, or any, depending on the 'which_quota' argument).  If the root is
+ * reached, set the realmp with the root ceph_snap_realm instead.
+ *
+ * Note that the caller is responsible for calling ceph_put_snap_realm() on the
+ * returned realm.
+ *
+ * Callers of this function need to hold mdsc->snap_rwsem.  However, if there's
+ * a need to do an inode lookup, this rwsem will be temporarily dropped.  Hence
+ * the 'retry' argument: if rwsem needs to be dropped and 'retry' is 'false'
+ * this function will return -EAGAIN; otherwise, the snaprealms walk-through
+ * will be restarted.
+ */
+static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode,
+			   enum quota_get_realm which_quota,
+			   struct ceph_snap_realm **realmp, bool retry)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_inode_info *ci = NULL;
+	struct ceph_snap_realm *realm, *next;
+	struct inode *in;
+	bool has_quota;
+
+	if (realmp)
+		*realmp = NULL;
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return 0;
+
+restart:
+	realm = ceph_inode(inode)->i_snap_realm;
+	if (realm) {
+		ceph_get_snap_realm(mdsc, realm);
+	} else {
+		/*
+		 * i_snap_realm is NULL when all caps have been released, e.g.
+		 * after an MDS session rejection. This is a transient state;
+		 * the realm will be restored once caps are re-granted.
+		 * Treat it as "no quota realm found".
+		 */
+		doutc(cl, "%p %llx.%llx null i_snap_realm\n",
+		      inode, ceph_vinop(inode));
+	}
+
+	while (realm) {
+		bool has_inode;
+
+		spin_lock(&realm->inodes_with_caps_lock);
+		has_inode = realm->inode;
+		in = has_inode ? igrab(realm->inode) : NULL;
+		spin_unlock(&realm->inodes_with_caps_lock);
+		if (has_inode && !in)
+			break;
+		if (!in) {
+			up_read(&mdsc->snap_rwsem);
+			in = lookup_quotarealm_inode(mdsc, inode->i_sb, realm);
+			down_read(&mdsc->snap_rwsem);
+			if (IS_ERR_OR_NULL(in))
+				break;
+			ceph_put_snap_realm(mdsc, realm);
+			if (!retry)
+				return -EAGAIN;
+			goto restart;
+		}
+
+		ci = ceph_inode(in);
+		has_quota = __ceph_has_quota(ci, which_quota);
+		iput(in);
+
+		next = realm->parent;
+		if (has_quota || !next) {
+			if (realmp)
+				*realmp = realm;
+			return 0;
+		}
+
+		ceph_get_snap_realm(mdsc, next);
+		ceph_put_snap_realm(mdsc, realm);
+		realm = next;
+	}
+	if (realm)
+		ceph_put_snap_realm(mdsc, realm);
+
+	return 0;
+}
+
+bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old->i_sb);
+	struct ceph_snap_realm *old_realm, *new_realm;
+	bool is_same;
+	int ret;
+
+restart:
+	/*
+	 * We need to lookup 2 quota realms atomically, i.e. with snap_rwsem.
+	 * However, get_quota_realm may drop it temporarily.  By setting the
+	 * 'retry' parameter to 'false', we'll get -EAGAIN if the rwsem was
+	 * dropped and we can then restart the whole operation.
+	 */
+	down_read(&mdsc->snap_rwsem);
+	get_quota_realm(mdsc, old, QUOTA_GET_ANY, &old_realm, true);
+	ret = get_quota_realm(mdsc, new, QUOTA_GET_ANY, &new_realm, false);
+	if (ret == -EAGAIN) {
+		up_read(&mdsc->snap_rwsem);
+		if (old_realm)
+			ceph_put_snap_realm(mdsc, old_realm);
+		goto restart;
+	}
+	is_same = (old_realm == new_realm);
+	up_read(&mdsc->snap_rwsem);
+
+	if (old_realm)
+		ceph_put_snap_realm(mdsc, old_realm);
+	if (new_realm)
+		ceph_put_snap_realm(mdsc, new_realm);
+
+	return is_same;
+}
+
+enum quota_check_op {
+	QUOTA_CHECK_MAX_FILES_OP,	/* check quota max_files limit */
+	QUOTA_CHECK_MAX_BYTES_OP,	/* check quota max_files limit */
+	QUOTA_CHECK_MAX_BYTES_APPROACHING_OP	/* check if quota max_files
+						   limit is approaching */
+};
+
+/*
+ * check_quota_exceeded() will walk up the snaprealm hierarchy and, for each
+ * realm, it will execute quota check operation defined by the 'op' parameter.
+ * The snaprealm walk is interrupted if the quota check detects that the quota
+ * is exceeded or if the root inode is reached.
+ */
+static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op,
+				 loff_t delta)
+{
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_inode_info *ci;
+	struct ceph_snap_realm *realm, *next;
+	struct inode *in;
+	u64 max, rvalue;
+	bool exceeded = false;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return false;
+
+	down_read(&mdsc->snap_rwsem);
+restart:
+	realm = ceph_inode(inode)->i_snap_realm;
+	if (realm) {
+		ceph_get_snap_realm(mdsc, realm);
+	} else {
+		/*
+		 * i_snap_realm is NULL when all caps have been released, e.g.
+		 * after an MDS session rejection. This is a transient state;
+		 * the realm will be restored once caps are re-granted.
+		 * Treat it as "quota not exceeded".
+		 */
+		doutc(cl, "%p %llx.%llx null i_snap_realm\n",
+		      inode, ceph_vinop(inode));
+	}
+
+	while (realm) {
+		bool has_inode;
+
+		spin_lock(&realm->inodes_with_caps_lock);
+		has_inode = realm->inode;
+		in = has_inode ? igrab(realm->inode) : NULL;
+		spin_unlock(&realm->inodes_with_caps_lock);
+		if (has_inode && !in)
+			break;
+		if (!in) {
+			up_read(&mdsc->snap_rwsem);
+			in = lookup_quotarealm_inode(mdsc, inode->i_sb, realm);
+			down_read(&mdsc->snap_rwsem);
+			if (IS_ERR_OR_NULL(in))
+				break;
+			ceph_put_snap_realm(mdsc, realm);
+			goto restart;
+		}
+		ci = ceph_inode(in);
+		spin_lock(&ci->i_ceph_lock);
+		if (op == QUOTA_CHECK_MAX_FILES_OP) {
+			max = ci->i_max_files;
+			rvalue = ci->i_rfiles + ci->i_rsubdirs;
+		} else {
+			max = ci->i_max_bytes;
+			rvalue = ci->i_rbytes;
+		}
+		spin_unlock(&ci->i_ceph_lock);
+		switch (op) {
+		case QUOTA_CHECK_MAX_FILES_OP:
+		case QUOTA_CHECK_MAX_BYTES_OP:
+			exceeded = (max && (rvalue + delta > max));
+			break;
+		case QUOTA_CHECK_MAX_BYTES_APPROACHING_OP:
+			if (max) {
+				if (rvalue >= max)
+					exceeded = true;
+				else {
+					/*
+					 * when we're writing more that 1/16th
+					 * of the available space
+					 */
+					exceeded =
+						(((max - rvalue) >> 4) < delta);
+				}
+			}
+			break;
+		default:
+			/* Shouldn't happen */
+			pr_warn_client(cl, "Invalid quota check op (%d)\n", op);
+			exceeded = true; /* Just break the loop */
+		}
+		iput(in);
+
+		next = realm->parent;
+		if (exceeded || !next)
+			break;
+		ceph_get_snap_realm(mdsc, next);
+		ceph_put_snap_realm(mdsc, realm);
+		realm = next;
+	}
+	if (realm)
+		ceph_put_snap_realm(mdsc, realm);
+	up_read(&mdsc->snap_rwsem);
+
+	return exceeded;
+}
+
+/*
+ * ceph_quota_is_max_files_exceeded - check if we can create a new file
+ * @inode:	directory where a new file is being created
+ *
+ * This functions returns true is max_files quota allows a new file to be
+ * created.  It is necessary to walk through the snaprealm hierarchy (until the
+ * FS root) to check all realms with quotas set.
+ */
+bool ceph_quota_is_max_files_exceeded(struct inode *inode)
+{
+	if (!ceph_has_realms_with_quotas(inode))
+		return false;
+
+	WARN_ON(!S_ISDIR(inode->i_mode));
+
+	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_FILES_OP, 1);
+}
+
+/*
+ * ceph_quota_is_max_bytes_exceeded - check if we can write to a file
+ * @inode:	inode being written
+ * @newsize:	new size if write succeeds
+ *
+ * This functions returns true is max_bytes quota allows a file size to reach
+ * @newsize; it returns false otherwise.
+ */
+bool ceph_quota_is_max_bytes_exceeded(struct inode *inode, loff_t newsize)
+{
+	loff_t size = i_size_read(inode);
+
+	if (!ceph_has_realms_with_quotas(inode))
+		return false;
+
+	/* return immediately if we're decreasing file size */
+	if (newsize <= size)
+		return false;
+
+	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_BYTES_OP, (newsize - size));
+}
+
+/*
+ * ceph_quota_is_max_bytes_approaching - check if we're reaching max_bytes
+ * @inode:	inode being written
+ * @newsize:	new size if write succeeds
+ *
+ * This function returns true if the new file size @newsize will be consuming
+ * more than 1/16th of the available quota space; it returns false otherwise.
+ */
+bool ceph_quota_is_max_bytes_approaching(struct inode *inode, loff_t newsize)
+{
+	loff_t size = ceph_inode(inode)->i_reported_size;
+
+	if (!ceph_has_realms_with_quotas(inode))
+		return false;
+
+	/* return immediately if we're decreasing file size */
+	if (newsize <= size)
+		return false;
+
+	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_BYTES_APPROACHING_OP,
+				    (newsize - size));
+}
+
+/*
+ * ceph_quota_update_statfs - if root has quota update statfs with quota status
+ * @fsc:	filesystem client instance
+ * @buf:	statfs to update
+ *
+ * If the mounted filesystem root has max_bytes quota set, update the filesystem
+ * statistics with the quota status.
+ *
+ * This function returns true if the stats have been updated, false otherwise.
+ */
+bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
+{
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_inode_info *ci;
+	struct ceph_snap_realm *realm;
+	struct inode *in;
+	u64 total = 0, used, free;
+	bool is_updated = false;
+
+	if (!ceph_has_realms_with_quotas(d_inode(fsc->sb->s_root)))
+		return false;
+
+	down_read(&mdsc->snap_rwsem);
+	get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES,
+			&realm, true);
+	up_read(&mdsc->snap_rwsem);
+	if (!realm)
+		return false;
+
+	spin_lock(&realm->inodes_with_caps_lock);
+	in = realm->inode ? igrab(realm->inode) : NULL;
+	spin_unlock(&realm->inodes_with_caps_lock);
+	if (in) {
+		ci = ceph_inode(in);
+		spin_lock(&ci->i_ceph_lock);
+		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) {
+			buf->f_blocks = total;
+			buf->f_bfree = free;
+			buf->f_bavail = free;
+			is_updated = true;
+		}
+		iput(in);
+	}
+	ceph_put_snap_realm(mdsc, realm);
+
+	return is_updated;
+}
+

linux-7.2.3/fs/ceph/strings.c

@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ceph fs string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+
+const char *ceph_mds_state_name(int s)
+{
+	switch (s) {
+		/* down and out */
+	case CEPH_MDS_STATE_DNE:        return "down:dne";
+	case CEPH_MDS_STATE_STOPPED:    return "down:stopped";
+		/* up and out */
+	case CEPH_MDS_STATE_BOOT:       return "up:boot";
+	case CEPH_MDS_STATE_STANDBY:    return "up:standby";
+	case CEPH_MDS_STATE_STANDBY_REPLAY:    return "up:standby-replay";
+	case CEPH_MDS_STATE_REPLAYONCE: return "up:oneshot-replay";
+	case CEPH_MDS_STATE_CREATING:   return "up:creating";
+	case CEPH_MDS_STATE_STARTING:   return "up:starting";
+		/* up and in */
+	case CEPH_MDS_STATE_REPLAY:     return "up:replay";
+	case CEPH_MDS_STATE_RESOLVE:    return "up:resolve";
+	case CEPH_MDS_STATE_RECONNECT:  return "up:reconnect";
+	case CEPH_MDS_STATE_REJOIN:     return "up:rejoin";
+	case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay";
+	case CEPH_MDS_STATE_ACTIVE:     return "up:active";
+	case CEPH_MDS_STATE_STOPPING:   return "up:stopping";
+	}
+	return "???";
+}
+
+const char *ceph_session_op_name(int op)
+{
+	switch (op) {
+	case CEPH_SESSION_REQUEST_OPEN: return "request_open";
+	case CEPH_SESSION_OPEN: return "open";
+	case CEPH_SESSION_REQUEST_CLOSE: return "request_close";
+	case CEPH_SESSION_CLOSE: return "close";
+	case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps";
+	case CEPH_SESSION_RENEWCAPS: return "renewcaps";
+	case CEPH_SESSION_STALE: return "stale";
+	case CEPH_SESSION_RECALL_STATE: return "recall_state";
+	case CEPH_SESSION_FLUSHMSG: return "flushmsg";
+	case CEPH_SESSION_FLUSHMSG_ACK: return "flushmsg_ack";
+	case CEPH_SESSION_FORCE_RO: return "force_ro";
+	case CEPH_SESSION_REJECT: return "reject";
+	case CEPH_SESSION_REQUEST_FLUSH_MDLOG: return "flush_mdlog";
+	}
+	return "???";
+}
+
+const char *ceph_mds_op_name(int op)
+{
+	switch (op) {
+	case CEPH_MDS_OP_LOOKUP:  return "lookup";
+	case CEPH_MDS_OP_LOOKUPHASH:  return "lookuphash";
+	case CEPH_MDS_OP_LOOKUPPARENT:  return "lookupparent";
+	case CEPH_MDS_OP_LOOKUPINO:  return "lookupino";
+	case CEPH_MDS_OP_LOOKUPNAME:  return "lookupname";
+	case CEPH_MDS_OP_GETATTR:  return "getattr";
+	case CEPH_MDS_OP_GETVXATTR:  return "getvxattr";
+	case CEPH_MDS_OP_SETXATTR: return "setxattr";
+	case CEPH_MDS_OP_SETATTR: return "setattr";
+	case CEPH_MDS_OP_RMXATTR: return "rmxattr";
+	case CEPH_MDS_OP_SETLAYOUT: return "setlayou";
+	case CEPH_MDS_OP_SETDIRLAYOUT: return "setdirlayout";
+	case CEPH_MDS_OP_READDIR: return "readdir";
+	case CEPH_MDS_OP_MKNOD: return "mknod";
+	case CEPH_MDS_OP_LINK: return "link";
+	case CEPH_MDS_OP_UNLINK: return "unlink";
+	case CEPH_MDS_OP_RENAME: return "rename";
+	case CEPH_MDS_OP_MKDIR: return "mkdir";
+	case CEPH_MDS_OP_RMDIR: return "rmdir";
+	case CEPH_MDS_OP_SYMLINK: return "symlink";
+	case CEPH_MDS_OP_CREATE: return "create";
+	case CEPH_MDS_OP_OPEN: return "open";
+	case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap";
+	case CEPH_MDS_OP_LSSNAP: return "lssnap";
+	case CEPH_MDS_OP_MKSNAP: return "mksnap";
+	case CEPH_MDS_OP_RMSNAP: return "rmsnap";
+	case CEPH_MDS_OP_RENAMESNAP: return "renamesnap";
+	case CEPH_MDS_OP_SETFILELOCK: return "setfilelock";
+	case CEPH_MDS_OP_GETFILELOCK: return "getfilelock";
+	}
+	return "???";
+}
+
+const char *ceph_cap_op_name(int op)
+{
+	switch (op) {
+	case CEPH_CAP_OP_GRANT: return "grant";
+	case CEPH_CAP_OP_REVOKE: return "revoke";
+	case CEPH_CAP_OP_TRUNC: return "trunc";
+	case CEPH_CAP_OP_EXPORT: return "export";
+	case CEPH_CAP_OP_IMPORT: return "import";
+	case CEPH_CAP_OP_UPDATE: return "update";
+	case CEPH_CAP_OP_DROP: return "drop";
+	case CEPH_CAP_OP_FLUSH: return "flush";
+	case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack";
+	case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap";
+	case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack";
+	case CEPH_CAP_OP_RELEASE: return "release";
+	case CEPH_CAP_OP_RENEW: return "renew";
+	}
+	return "???";
+}
+
+const char *ceph_lease_op_name(int o)
+{
+	switch (o) {
+	case CEPH_MDS_LEASE_REVOKE: return "revoke";
+	case CEPH_MDS_LEASE_RELEASE: return "release";
+	case CEPH_MDS_LEASE_RENEW: return "renew";
+	case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack";
+	}
+	return "???";
+}
+
+const char *ceph_snap_op_name(int o)
+{
+	switch (o) {
+	case CEPH_SNAP_OP_UPDATE: return "update";
+	case CEPH_SNAP_OP_CREATE: return "create";
+	case CEPH_SNAP_OP_DESTROY: return "destroy";
+	case CEPH_SNAP_OP_SPLIT: return "split";
+	}
+	return "???";
+}

linux-7.2.3/fs/ceph/subvolume_metrics.c

@@ -0,0 +1,416 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+
+#include "subvolume_metrics.h"
+#include "mds_client.h"
+#include "super.h"
+
+/**
+ * struct ceph_subvol_metric_rb_entry - Per-subvolume I/O metrics node
+ * @node: Red-black tree linkage for tracker->tree
+ * @subvolume_id: Subvolume identifier (key for rb-tree lookup)
+ * @read_ops: Accumulated read operation count since last snapshot
+ * @write_ops: Accumulated write operation count since last snapshot
+ * @read_bytes: Accumulated bytes read since last snapshot
+ * @write_bytes: Accumulated bytes written since last snapshot
+ * @read_latency_us: Sum of read latencies in microseconds
+ * @write_latency_us: Sum of write latencies in microseconds
+ */
+struct ceph_subvol_metric_rb_entry {
+	struct rb_node node;
+	u64 subvolume_id;
+	u64 read_ops;
+	u64 write_ops;
+	u64 read_bytes;
+	u64 write_bytes;
+	u64 read_latency_us;
+	u64 write_latency_us;
+};
+
+static struct kmem_cache *ceph_subvol_metric_entry_cachep;
+
+void ceph_subvolume_metrics_init(struct ceph_subvolume_metrics_tracker *tracker)
+{
+	spin_lock_init(&tracker->lock);
+	tracker->tree = RB_ROOT_CACHED;
+	tracker->nr_entries = 0;
+	tracker->enabled = false;
+	atomic64_set(&tracker->snapshot_attempts, 0);
+	atomic64_set(&tracker->snapshot_empty, 0);
+	atomic64_set(&tracker->snapshot_failures, 0);
+	atomic64_set(&tracker->record_calls, 0);
+	atomic64_set(&tracker->record_disabled, 0);
+	atomic64_set(&tracker->record_no_subvol, 0);
+	atomic64_set(&tracker->total_read_ops, 0);
+	atomic64_set(&tracker->total_read_bytes, 0);
+	atomic64_set(&tracker->total_write_ops, 0);
+	atomic64_set(&tracker->total_write_bytes, 0);
+}
+
+static struct ceph_subvol_metric_rb_entry *
+__lookup_entry(struct ceph_subvolume_metrics_tracker *tracker, u64 subvol_id)
+{
+	struct rb_node *node;
+
+	node = tracker->tree.rb_root.rb_node;
+	while (node) {
+		struct ceph_subvol_metric_rb_entry *entry =
+			rb_entry(node, struct ceph_subvol_metric_rb_entry, node);
+
+		if (subvol_id < entry->subvolume_id)
+			node = node->rb_left;
+		else if (subvol_id > entry->subvolume_id)
+			node = node->rb_right;
+		else
+			return entry;
+	}
+
+	return NULL;
+}
+
+static struct ceph_subvol_metric_rb_entry *
+__insert_entry(struct ceph_subvolume_metrics_tracker *tracker,
+	       struct ceph_subvol_metric_rb_entry *entry)
+{
+	struct rb_node **link = &tracker->tree.rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	bool leftmost = true;
+
+	while (*link) {
+		struct ceph_subvol_metric_rb_entry *cur =
+			rb_entry(*link, struct ceph_subvol_metric_rb_entry, node);
+
+		parent = *link;
+		if (entry->subvolume_id < cur->subvolume_id)
+			link = &(*link)->rb_left;
+		else if (entry->subvolume_id > cur->subvolume_id) {
+			link = &(*link)->rb_right;
+			leftmost = false;
+		} else
+			return cur;
+	}
+
+	rb_link_node(&entry->node, parent, link);
+	rb_insert_color_cached(&entry->node, &tracker->tree, leftmost);
+	tracker->nr_entries++;
+	return entry;
+}
+
+static void ceph_subvolume_metrics_clear_locked(
+		struct ceph_subvolume_metrics_tracker *tracker)
+{
+	struct rb_node *node = rb_first_cached(&tracker->tree);
+
+	while (node) {
+		struct ceph_subvol_metric_rb_entry *entry =
+			rb_entry(node, struct ceph_subvol_metric_rb_entry, node);
+		struct rb_node *next = rb_next(node);
+
+		rb_erase_cached(&entry->node, &tracker->tree);
+		tracker->nr_entries--;
+		kmem_cache_free(ceph_subvol_metric_entry_cachep, entry);
+		node = next;
+	}
+
+	tracker->tree = RB_ROOT_CACHED;
+}
+
+void ceph_subvolume_metrics_destroy(struct ceph_subvolume_metrics_tracker *tracker)
+{
+	spin_lock(&tracker->lock);
+	ceph_subvolume_metrics_clear_locked(tracker);
+	tracker->enabled = false;
+	spin_unlock(&tracker->lock);
+}
+
+void ceph_subvolume_metrics_enable(struct ceph_subvolume_metrics_tracker *tracker,
+				   bool enable)
+{
+	spin_lock(&tracker->lock);
+	if (enable) {
+		tracker->enabled = true;
+	} else {
+		tracker->enabled = false;
+		ceph_subvolume_metrics_clear_locked(tracker);
+	}
+	spin_unlock(&tracker->lock);
+}
+
+void ceph_subvolume_metrics_record(struct ceph_subvolume_metrics_tracker *tracker,
+				   u64 subvol_id, bool is_write,
+				   size_t size, u64 latency_us)
+{
+	struct ceph_subvol_metric_rb_entry *entry, *new_entry = NULL;
+	bool retry = false;
+
+	/* CEPH_SUBVOLUME_ID_NONE (0) means unknown/unset subvolume */
+	if (!READ_ONCE(tracker->enabled) ||
+	    subvol_id == CEPH_SUBVOLUME_ID_NONE || !size || !latency_us)
+		return;
+
+	/*
+	 * Retry loop for lock-free allocation pattern:
+	 * 1. First iteration: lookup under lock, if miss -> drop lock, alloc, retry
+	 * 2. Second iteration: lookup again (may have been inserted), insert if still missing
+	 * 3. On race (another thread inserted same key): free our alloc, retry
+	 * All successful paths exit via return, so retry flag doesn't need reset.
+	 */
+	do {
+		spin_lock(&tracker->lock);
+		if (!tracker->enabled) {
+			spin_unlock(&tracker->lock);
+			if (new_entry)
+				kmem_cache_free(ceph_subvol_metric_entry_cachep, new_entry);
+			return;
+		}
+
+		entry = __lookup_entry(tracker, subvol_id);
+		if (!entry) {
+			if (!new_entry) {
+				spin_unlock(&tracker->lock);
+				new_entry = kmem_cache_zalloc(ceph_subvol_metric_entry_cachep,
+						      GFP_NOFS);
+				if (!new_entry)
+					return;
+				new_entry->subvolume_id = subvol_id;
+				retry = true;
+				continue;
+			}
+			entry = __insert_entry(tracker, new_entry);
+			if (entry != new_entry) {
+				/* raced with another insert */
+				spin_unlock(&tracker->lock);
+				kmem_cache_free(ceph_subvol_metric_entry_cachep, new_entry);
+				new_entry = NULL;
+				retry = true;
+				continue;
+			}
+			new_entry = NULL;
+		}
+
+		if (is_write) {
+			entry->write_ops++;
+			entry->write_bytes += size;
+			entry->write_latency_us += latency_us;
+			atomic64_inc(&tracker->total_write_ops);
+			atomic64_add(size, &tracker->total_write_bytes);
+		} else {
+			entry->read_ops++;
+			entry->read_bytes += size;
+			entry->read_latency_us += latency_us;
+			atomic64_inc(&tracker->total_read_ops);
+			atomic64_add(size, &tracker->total_read_bytes);
+		}
+		spin_unlock(&tracker->lock);
+		if (new_entry)
+			kmem_cache_free(ceph_subvol_metric_entry_cachep, new_entry);
+		return;
+	} while (retry);
+}
+
+int ceph_subvolume_metrics_snapshot(struct ceph_subvolume_metrics_tracker *tracker,
+				    struct ceph_subvol_metric_snapshot **out,
+				    u32 *nr, bool consume)
+{
+	struct ceph_subvol_metric_snapshot *snap = NULL;
+	struct rb_node *node;
+	u32 count = 0, idx = 0;
+	int ret = 0;
+
+	*out = NULL;
+	*nr = 0;
+
+	if (!READ_ONCE(tracker->enabled))
+		return 0;
+
+	atomic64_inc(&tracker->snapshot_attempts);
+
+	spin_lock(&tracker->lock);
+	for (node = rb_first_cached(&tracker->tree); node; node = rb_next(node)) {
+		struct ceph_subvol_metric_rb_entry *entry =
+			rb_entry(node, struct ceph_subvol_metric_rb_entry, node);
+
+		/* Include entries with ANY I/O activity (read OR write) */
+		if (entry->read_ops || entry->write_ops)
+			count++;
+	}
+	spin_unlock(&tracker->lock);
+
+	if (!count) {
+		atomic64_inc(&tracker->snapshot_empty);
+		return 0;
+	}
+
+	snap = kcalloc(count, sizeof(*snap), GFP_NOFS);
+	if (!snap) {
+		atomic64_inc(&tracker->snapshot_failures);
+		return -ENOMEM;
+	}
+
+	spin_lock(&tracker->lock);
+	node = rb_first_cached(&tracker->tree);
+	while (node) {
+		struct ceph_subvol_metric_rb_entry *entry =
+			rb_entry(node, struct ceph_subvol_metric_rb_entry, node);
+		struct rb_node *next = rb_next(node);
+
+		/* Skip entries with NO I/O activity at all */
+		if (!entry->read_ops && !entry->write_ops) {
+			rb_erase_cached(&entry->node, &tracker->tree);
+			tracker->nr_entries--;
+			kmem_cache_free(ceph_subvol_metric_entry_cachep, entry);
+			node = next;
+			continue;
+		}
+
+		if (idx >= count) {
+			pr_warn("ceph: subvol metrics snapshot race (idx=%u count=%u)\n",
+				idx, count);
+			break;
+		}
+
+		snap[idx].subvolume_id = entry->subvolume_id;
+		snap[idx].read_ops = entry->read_ops;
+		snap[idx].write_ops = entry->write_ops;
+		snap[idx].read_bytes = entry->read_bytes;
+		snap[idx].write_bytes = entry->write_bytes;
+		snap[idx].read_latency_us = entry->read_latency_us;
+		snap[idx].write_latency_us = entry->write_latency_us;
+		idx++;
+
+		if (consume) {
+			entry->read_ops = 0;
+			entry->write_ops = 0;
+			entry->read_bytes = 0;
+			entry->write_bytes = 0;
+			entry->read_latency_us = 0;
+			entry->write_latency_us = 0;
+			rb_erase_cached(&entry->node, &tracker->tree);
+			tracker->nr_entries--;
+			kmem_cache_free(ceph_subvol_metric_entry_cachep, entry);
+		}
+		node = next;
+	}
+	spin_unlock(&tracker->lock);
+
+	if (!idx) {
+		kfree(snap);
+		snap = NULL;
+		ret = 0;
+	} else {
+		*nr = idx;
+		*out = snap;
+	}
+
+	return ret;
+}
+
+void ceph_subvolume_metrics_free_snapshot(struct ceph_subvol_metric_snapshot *snapshot)
+{
+	kfree(snapshot);
+}
+
+/*
+ * Dump subvolume metrics to a seq_file for debugfs.
+ *
+ * Iterates the rb-tree directly under spinlock to avoid allocation.
+ * The lock hold time is minimal since we're only doing seq_printf calls.
+ */
+void ceph_subvolume_metrics_dump(struct ceph_subvolume_metrics_tracker *tracker,
+				 struct seq_file *s)
+{
+	struct rb_node *node;
+	bool found = false;
+
+	spin_lock(&tracker->lock);
+	if (!tracker->enabled) {
+		spin_unlock(&tracker->lock);
+		seq_puts(s, "subvolume metrics disabled\n");
+		return;
+	}
+
+	for (node = rb_first_cached(&tracker->tree); node; node = rb_next(node)) {
+		struct ceph_subvol_metric_rb_entry *entry =
+			rb_entry(node, struct ceph_subvol_metric_rb_entry, node);
+		u64 avg_rd_lat, avg_wr_lat;
+
+		if (!entry->read_ops && !entry->write_ops)
+			continue;
+
+		if (!found) {
+			seq_puts(s, "subvol_id       rd_ops    rd_bytes    rd_avg_lat_us  wr_ops    wr_bytes    wr_avg_lat_us\n");
+			seq_puts(s, "------------------------------------------------------------------------------------------------\n");
+			found = true;
+		}
+
+		avg_rd_lat = entry->read_ops ?
+			div64_u64(entry->read_latency_us, entry->read_ops) : 0;
+		avg_wr_lat = entry->write_ops ?
+			div64_u64(entry->write_latency_us, entry->write_ops) : 0;
+
+		seq_printf(s, "%-15llu%-10llu%-12llu%-16llu%-10llu%-12llu%-16llu\n",
+			   entry->subvolume_id,
+			   entry->read_ops,
+			   entry->read_bytes,
+			   avg_rd_lat,
+			   entry->write_ops,
+			   entry->write_bytes,
+			   avg_wr_lat);
+	}
+	spin_unlock(&tracker->lock);
+
+	if (!found)
+		seq_puts(s, "(no subvolume metrics collected)\n");
+}
+
+void ceph_subvolume_metrics_record_io(struct ceph_mds_client *mdsc,
+				      struct ceph_inode_info *ci,
+				      bool is_write, size_t bytes,
+				      ktime_t start, ktime_t end)
+{
+	struct ceph_subvolume_metrics_tracker *tracker;
+	u64 subvol_id;
+	s64 delta_us;
+
+	if (!mdsc || !ci || !bytes)
+		return;
+
+	tracker = &mdsc->subvol_metrics;
+	atomic64_inc(&tracker->record_calls);
+
+	if (!ceph_subvolume_metrics_enabled(tracker)) {
+		atomic64_inc(&tracker->record_disabled);
+		return;
+	}
+
+	subvol_id = READ_ONCE(ci->i_subvolume_id);
+	if (subvol_id == CEPH_SUBVOLUME_ID_NONE) {
+		atomic64_inc(&tracker->record_no_subvol);
+		return;
+	}
+
+	delta_us = ktime_to_us(ktime_sub(end, start));
+	if (delta_us <= 0)
+		delta_us = 1;
+
+	ceph_subvolume_metrics_record(tracker, subvol_id, is_write,
+				      bytes, (u64)delta_us);
+}
+
+int __init ceph_subvolume_metrics_cache_init(void)
+{
+	ceph_subvol_metric_entry_cachep = KMEM_CACHE(ceph_subvol_metric_rb_entry,
+						    SLAB_RECLAIM_ACCOUNT);
+	if (!ceph_subvol_metric_entry_cachep)
+		return -ENOMEM;
+	return 0;
+}
+
+void ceph_subvolume_metrics_cache_destroy(void)
+{
+	kmem_cache_destroy(ceph_subvol_metric_entry_cachep);
+}

linux-7.2.3/fs/ceph/subvolume_metrics.h

@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_SUBVOLUME_METRICS_H
+#define _FS_CEPH_SUBVOLUME_METRICS_H
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+#include <linux/atomic.h>
+
+struct seq_file;
+struct ceph_mds_client;
+struct ceph_inode_info;
+
+/**
+ * struct ceph_subvol_metric_snapshot - Point-in-time snapshot of subvolume metrics
+ * @subvolume_id: Subvolume identifier (inode number of subvolume root)
+ * @read_ops: Number of read operations since last snapshot
+ * @write_ops: Number of write operations since last snapshot
+ * @read_bytes: Total bytes read since last snapshot
+ * @write_bytes: Total bytes written since last snapshot
+ * @read_latency_us: Sum of read latencies in microseconds (for avg calculation)
+ * @write_latency_us: Sum of write latencies in microseconds (for avg calculation)
+ */
+struct ceph_subvol_metric_snapshot {
+	u64 subvolume_id;
+	u64 read_ops;
+	u64 write_ops;
+	u64 read_bytes;
+	u64 write_bytes;
+	u64 read_latency_us;
+	u64 write_latency_us;
+};
+
+/**
+ * struct ceph_subvolume_metrics_tracker - Tracks per-subvolume I/O metrics
+ * @lock: Protects @tree and @nr_entries during concurrent access
+ * @tree: Red-black tree of per-subvolume entries, keyed by subvolume_id
+ * @nr_entries: Number of entries currently in @tree
+ * @enabled: Whether collection is enabled (requires MDS feature support)
+ * @snapshot_attempts: Debug counter: total ceph_subvolume_metrics_snapshot() calls
+ * @snapshot_empty: Debug counter: snapshots that found no data to report
+ * @snapshot_failures: Debug counter: snapshots that failed to allocate memory
+ * @record_calls: Debug counter: total ceph_subvolume_metrics_record() calls
+ * @record_disabled: Debug counter: record calls skipped because disabled
+ * @record_no_subvol: Debug counter: record calls skipped (no subvolume_id)
+ * @total_read_ops: Cumulative read ops across all snapshots (never reset)
+ * @total_read_bytes: Cumulative bytes read across all snapshots (never reset)
+ * @total_write_ops: Cumulative write ops across all snapshots (never reset)
+ * @total_write_bytes: Cumulative bytes written across all snapshots (never reset)
+ */
+struct ceph_subvolume_metrics_tracker {
+	spinlock_t lock;
+	struct rb_root_cached tree;
+	u32 nr_entries;
+	bool enabled;
+	atomic64_t snapshot_attempts;
+	atomic64_t snapshot_empty;
+	atomic64_t snapshot_failures;
+	atomic64_t record_calls;
+	atomic64_t record_disabled;
+	atomic64_t record_no_subvol;
+	atomic64_t total_read_ops;
+	atomic64_t total_read_bytes;
+	atomic64_t total_write_ops;
+	atomic64_t total_write_bytes;
+};
+
+void ceph_subvolume_metrics_init(struct ceph_subvolume_metrics_tracker *tracker);
+void ceph_subvolume_metrics_destroy(struct ceph_subvolume_metrics_tracker *tracker);
+void ceph_subvolume_metrics_enable(struct ceph_subvolume_metrics_tracker *tracker,
+				   bool enable);
+void ceph_subvolume_metrics_record(struct ceph_subvolume_metrics_tracker *tracker,
+				   u64 subvol_id, bool is_write,
+				   size_t size, u64 latency_us);
+int ceph_subvolume_metrics_snapshot(struct ceph_subvolume_metrics_tracker *tracker,
+				    struct ceph_subvol_metric_snapshot **out,
+				    u32 *nr, bool consume);
+void ceph_subvolume_metrics_free_snapshot(struct ceph_subvol_metric_snapshot *snapshot);
+void ceph_subvolume_metrics_dump(struct ceph_subvolume_metrics_tracker *tracker,
+				 struct seq_file *s);
+
+void ceph_subvolume_metrics_record_io(struct ceph_mds_client *mdsc,
+				      struct ceph_inode_info *ci,
+				      bool is_write, size_t bytes,
+				      ktime_t start, ktime_t end);
+
+static inline bool ceph_subvolume_metrics_enabled(
+		const struct ceph_subvolume_metrics_tracker *tracker)
+{
+	return READ_ONCE(tracker->enabled);
+}
+
+int __init ceph_subvolume_metrics_cache_init(void);
+void ceph_subvolume_metrics_cache_destroy(void);
+
+#endif /* _FS_CEPH_SUBVOLUME_METRICS_H */

linux-7.2.3/fs/ceph/util.c

@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Some non-inline ceph helpers
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+/*
+ * return true if @layout appears to be valid
+ */
+int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
+{
+	__u32 su = layout->stripe_unit;
+	__u32 sc = layout->stripe_count;
+	__u32 os = layout->object_size;
+
+	/* stripe unit, object size must be non-zero, 64k increment */
+	if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1)))
+		return 0;
+	if (!os || (os & (CEPH_MIN_STRIPE_UNIT-1)))
+		return 0;
+	/* object size must be a multiple of stripe unit */
+	if (os < su || os % su)
+		return 0;
+	/* stripe count must be non-zero */
+	if (!sc)
+		return 0;
+	return 1;
+}
+
+void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
+				  struct ceph_file_layout_legacy *legacy)
+{
+	fl->stripe_unit = le32_to_cpu(legacy->fl_stripe_unit);
+	fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count);
+	fl->object_size = le32_to_cpu(legacy->fl_object_size);
+	fl->pool_id = le32_to_cpu(legacy->fl_pg_pool);
+	if (fl->pool_id == 0 && fl->stripe_unit == 0 &&
+	    fl->stripe_count == 0 && fl->object_size == 0)
+		fl->pool_id = -1;
+}
+
+void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
+				struct ceph_file_layout_legacy *legacy)
+{
+	legacy->fl_stripe_unit = cpu_to_le32(fl->stripe_unit);
+	legacy->fl_stripe_count = cpu_to_le32(fl->stripe_count);
+	legacy->fl_object_size = cpu_to_le32(fl->object_size);
+	if (fl->pool_id >= 0)
+		legacy->fl_pg_pool = cpu_to_le32(fl->pool_id);
+	else
+		legacy->fl_pg_pool = 0;
+}
+
+int ceph_flags_to_mode(int flags)
+{
+	int mode;
+
+#ifdef O_DIRECTORY  /* fixme */
+	if ((flags & O_DIRECTORY) == O_DIRECTORY)
+		return CEPH_FILE_MODE_PIN;
+#endif
+
+	switch (flags & O_ACCMODE) {
+	case O_WRONLY:
+		mode = CEPH_FILE_MODE_WR;
+		break;
+	case O_RDONLY:
+		mode = CEPH_FILE_MODE_RD;
+		break;
+	case O_RDWR:
+	case O_ACCMODE: /* this is what the VFS does */
+		mode = CEPH_FILE_MODE_RDWR;
+		break;
+	}
+#ifdef O_LAZY
+	if (flags & O_LAZY)
+		mode |= CEPH_FILE_MODE_LAZY;
+#endif
+
+	return mode;
+}
+
+int ceph_caps_for_mode(int mode)
+{
+	int caps = CEPH_CAP_PIN;
+
+	if (mode & CEPH_FILE_MODE_RD)
+		caps |= CEPH_CAP_FILE_SHARED |
+			CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE;
+	if (mode & CEPH_FILE_MODE_WR)
+		caps |= CEPH_CAP_FILE_EXCL |
+			CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |
+			CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL |
+			CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL;
+	if (mode & CEPH_FILE_MODE_LAZY)
+		caps |= CEPH_CAP_FILE_LAZYIO;
+
+	return caps;
+}