5.10.220-rc1 review

index ef06a2a384bea..c805ac8dd7e77 100644
@@ -277,19 +277,6 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 	return 1;
 }
 
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
-{
-	struct nfsd_attrstat *resp = rqstp->rq_resp;
-
-	*p++ = resp->status;
-	if (resp->status != nfs_ok)
-		goto out;
-
-	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
-	return xdr_ressize_check(rqstp, p);
-}
-
 /* ACCESS */
 static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {

@@ -317,13 +304,6 @@ static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
 	posix_acl_release(resp->acl_default);
 }
 
-static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
-{
-	struct nfsd_attrstat *resp = rqstp->rq_resp;
-
-	fh_put(&resp->fh);
-}
-
 static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
 {
 	struct nfsd3_accessres *resp = rqstp->rq_resp;

@@ -374,8 +354,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 	[ACLPROC2_GETATTR] = {
 		.pc_func = nfsacld_proc_getattr,
 		.pc_decode = nfssvc_decode_fhandleargs,
-		.pc_encode = nfsaclsvc_encode_attrstatres,
-		.pc_release = nfsaclsvc_release_attrstat,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,

index c805ac8dd7e77..8703326fc1654 100644
@@ -280,16 +280,21 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 /* ACCESS */
 static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_accessres *resp = rqstp->rq_resp;
 
-	*p++ = resp->status;
-	if (resp->status != nfs_ok)
-		goto out;
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return 0;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+			return 0;
+		if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+			return 0;
+		break;
+	}
 
-	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-	*p++ = htonl(resp->access);
-out:
-	return xdr_ressize_check(rqstp, p);
+	return 1;
 }
 
 /*

index 1fed3a8deb183..b800cfefcab7a 100644
@@ -201,64 +201,6 @@ svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	return true;
 }
 
-static __be32 *
-encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
-	     struct kstat *stat)
-{
-	struct user_namespace *userns = nfsd_user_namespace(rqstp);
-	struct dentry	*dentry = fhp->fh_dentry;
-	int type;
-	struct timespec64 time;
-	u32 f;
-
-	type = (stat->mode & S_IFMT);
-
-	*p++ = htonl(nfs_ftypes[type >> 12]);
-	*p++ = htonl((u32) stat->mode);
-	*p++ = htonl((u32) stat->nlink);
-	*p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
-	*p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
-
-	if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
-		*p++ = htonl(NFS_MAXPATHLEN);
-	} else {
-		*p++ = htonl((u32) stat->size);
-	}
-	*p++ = htonl((u32) stat->blksize);
-	if (S_ISCHR(type) || S_ISBLK(type))
-		*p++ = htonl(new_encode_dev(stat->rdev));
-	else
-		*p++ = htonl(0xffffffff);
-	*p++ = htonl((u32) stat->blocks);
-	switch (fsid_source(fhp)) {
-	default:
-	case FSIDSOURCE_DEV:
-		*p++ = htonl(new_encode_dev(stat->dev));
-		break;
-	case FSIDSOURCE_FSID:
-		*p++ = htonl((u32) fhp->fh_export->ex_fsid);
-		break;
-	case FSIDSOURCE_UUID:
-		f = ((u32*)fhp->fh_export->ex_uuid)[0];
-		f ^= ((u32*)fhp->fh_export->ex_uuid)[1];
-		f ^= ((u32*)fhp->fh_export->ex_uuid)[2];
-		f ^= ((u32*)fhp->fh_export->ex_uuid)[3];
-		*p++ = htonl(f);
-		break;
-	}
-	*p++ = htonl((u32) stat->ino);
-	*p++ = htonl((u32) stat->atime.tv_sec);
-	*p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
-	time = stat->mtime;
-	lease_get_mtime(d_inode(dentry), &time); 
-	*p++ = htonl((u32) time.tv_sec);
-	*p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0); 
-	*p++ = htonl((u32) stat->ctime.tv_sec);
-	*p++ = htonl(stat->ctime.tv_nsec ? stat->ctime.tv_nsec / 1000 : 0);
-
-	return p;
-}
-
 /**
  * svcxdr_encode_fattr - Encode NFSv2 file attributes
  * @rqstp: Context of a completed RPC transaction

@@ -328,12 +270,6 @@ svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	return true;
 }
 
-/* Helper function for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
-{
-	return encode_fattr(rqstp, p, fhp, stat);
-}
-
 /*
  * XDR decode functions
  */

index 8bcdc37398ab5..c67ad02b9a028 100644
@@ -168,7 +168,6 @@ void nfssvc_release_diropres(struct svc_rqst *rqstp);
 void nfssvc_release_readres(struct svc_rqst *rqstp);
 
 /* Helper functions for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
 bool svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp);
 bool svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status);
 bool svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,

index a568b842e9ebe..04e157b0b201a 100644
@@ -166,22 +166,25 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 /* GETACL */
 static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
+	struct kvec *head = rqstp->rq_res.head;
+	struct inode *inode = d_inode(dentry);
+	unsigned int base;
+	int n;
+	int w;
 
-	*p++ = resp->status;
-	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
-	if (resp->status == 0 && dentry && d_really_is_positive(dentry)) {
-		struct inode *inode = d_inode(dentry);
-		struct kvec *head = rqstp->rq_res.head;
-		unsigned int base;
-		int n;
-		int w;
-
-		*p++ = htonl(resp->mask);
-		if (!xdr_ressize_check(rqstp, p))
+	if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+		return 0;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
 			return 0;
-		base = (char *)p - (char *)head->iov_base;
+		if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
+			return 0;
+
+		base = (char *)xdr->p - (char *)head->iov_base;
 
 		rqstp->rq_res.page_len = w = nfsacl_size(
 			(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,

@@ -202,9 +205,11 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 					  NFS_ACL_DEFAULT);
 		if (n <= 0)
 			return 0;
-	} else
-		if (!xdr_ressize_check(rqstp, p))
+		break;
+	default:
+		if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
 			return 0;
+	}
 
 	return 1;
 }

index 646bbfc5b7794..941740a97f8f5 100644
@@ -107,7 +107,16 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp)
 	return true;
 }
 
-static bool
+/**
+ * svcxdr_encode_nfsstat3 - Encode an NFSv3 status code
+ * @xdr: XDR stream
+ * @status: status value to encode
+ *
+ * Return values:
+ *   %false: Send buffer space was exhausted
+ *   %true: Success
+ */
+bool
 svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status)
 {
 	__be32 *p;

@@ -464,7 +473,17 @@ svcxdr_encode_pre_op_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
 	return svcxdr_encode_wcc_attr(xdr, fhp);
 }
 
-static bool
+/**
+ * svcxdr_encode_post_op_attr - Encode NFSv3 post-op attributes
+ * @rqstp: Context of a completed RPC transaction
+ * @xdr: XDR stream
+ * @fhp: File handle to encode
+ *
+ * Return values:
+ *   %false: Send buffer space was exhausted
+ *   %true: Success
+ */
+bool
 svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 			   const struct svc_fh *fhp)
 {

index b851458373db6..746c5f79964f1 100644
@@ -308,5 +308,8 @@ int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
 __be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p,
 				struct svc_fh *fhp);
 bool svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+				const struct svc_fh *fhp);
 
 #endif /* _LINUX_NFSD_XDR3_H */

index 04e157b0b201a..cfb686f23e571 100644
@@ -217,11 +217,11 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 /* SETACL */
 static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 
-	*p++ = resp->status;
-	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
-	return xdr_ressize_check(rqstp, p);
+	return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+		svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh);
 }
 
 /*

index 941740a97f8f5..fcfa0d611b931 100644
@@ -48,13 +48,6 @@ static const u32 nfs3_ftypes[] = {
  * Basic NFSv3 data types (RFC 1813 Sections 2.5 and 2.6)
  */
 
-static __be32 *
-encode_time3(__be32 *p, struct timespec64 *time)
-{
-	*p++ = htonl((u32) time->tv_sec); *p++ = htonl(time->tv_nsec);
-	return p;
-}
-
 static __be32 *
 encode_nfstime3(__be32 *p, const struct timespec64 *time)
 {

@@ -396,54 +389,6 @@ svcxdr_encode_fattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	return true;
 }
 
-static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp)
-{
-	u64 f;
-	switch(fsid_source(fhp)) {
-	default:
-	case FSIDSOURCE_DEV:
-		p = xdr_encode_hyper(p, (u64)huge_encode_dev
-				     (fhp->fh_dentry->d_sb->s_dev));
-		break;
-	case FSIDSOURCE_FSID:
-		p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
-		break;
-	case FSIDSOURCE_UUID:
-		f = ((u64*)fhp->fh_export->ex_uuid)[0];
-		f ^= ((u64*)fhp->fh_export->ex_uuid)[1];
-		p = xdr_encode_hyper(p, f);
-		break;
-	}
-	return p;
-}
-
-static __be32 *
-encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
-	      struct kstat *stat)
-{
-	struct user_namespace *userns = nfsd_user_namespace(rqstp);
-	*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
-	*p++ = htonl((u32) (stat->mode & S_IALLUGO));
-	*p++ = htonl((u32) stat->nlink);
-	*p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
-	*p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
-	if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) {
-		p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN);
-	} else {
-		p = xdr_encode_hyper(p, (u64) stat->size);
-	}
-	p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
-	*p++ = htonl((u32) MAJOR(stat->rdev));
-	*p++ = htonl((u32) MINOR(stat->rdev));
-	p = encode_fsid(p, fhp);
-	p = xdr_encode_hyper(p, stat->ino);
-	p = encode_time3(p, &stat->atime);
-	p = encode_time3(p, &stat->mtime);
-	p = encode_time3(p, &stat->ctime);
-
-	return p;
-}
-
 static bool
 svcxdr_encode_wcc_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
 {

@@ -512,37 +457,6 @@ svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	return xdr_stream_encode_item_absent(xdr) > 0;
 }
 
-/*
- * Encode post-operation attributes.
- * The inode may be NULL if the call failed because of a stale file
- * handle. In this case, no attributes are returned.
- */
-static __be32 *
-encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
-{
-	struct dentry *dentry = fhp->fh_dentry;
-	if (!fhp->fh_no_wcc && dentry && d_really_is_positive(dentry)) {
-	        __be32 err;
-		struct kstat stat;
-
-		err = fh_getattr(fhp, &stat);
-		if (!err) {
-			*p++ = xdr_one;		/* attributes follow */
-			lease_get_mtime(d_inode(dentry), &stat.mtime);
-			return encode_fattr3(rqstp, p, fhp, &stat);
-		}
-	}
-	*p++ = xdr_zero;
-	return p;
-}
-
-/* Helper for NFSv3 ACLs */
-__be32 *
-nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
-{
-	return encode_post_op_attr(rqstp, p, fhp);
-}
-
 /*
  * Encode weak cache consistency data
  */

index 746c5f79964f1..933008382bbeb 100644
@@ -305,8 +305,6 @@ int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
 int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
 			      loff_t offset, u64 ino, unsigned int d_type);
 /* Helper functions for NFSv3 ACL code */
-__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p,
-				struct svc_fh *fhp);
 bool svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp);
 bool svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status);
 bool svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,

index 2bc2a888f7fa8..d20ab767ba26a 100644
@@ -391,6 +391,30 @@ DEFINE_EVENT(nfsd_err_class, nfsd_##name,	\
 DEFINE_NFSD_ERR_EVENT(read_err);
 DEFINE_NFSD_ERR_EVENT(write_err);
 
+TRACE_EVENT(nfsd_dirent,
+	TP_PROTO(struct svc_fh *fhp,
+		 u64 ino,
+		 const char *name,
+		 int namlen),
+	TP_ARGS(fhp, ino, name, namlen),
+	TP_STRUCT__entry(
+		__field(u32, fh_hash)
+		__field(u64, ino)
+		__field(int, len)
+		__dynamic_array(unsigned char, name, namlen)
+	),
+	TP_fast_assign(
+		__entry->fh_hash = fhp ? knfsd_fh_hash(&fhp->fh_handle) : 0;
+		__entry->ino = ino;
+		__entry->len = namlen;
+		memcpy(__get_str(name), name, namlen);
+		__assign_str(name, name);
+	),
+	TP_printk("fh_hash=0x%08x ino=%llu name=%.*s",
+		__entry->fh_hash, __entry->ino,
+		__entry->len, __get_str(name))
+)
+
 #include "state.h"
 #include "filecache.h"
 #include "vfs.h"

index d12c3e71ca10e..520e55c35e742 100644
@@ -1979,8 +1979,9 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
 	return 0;
 }
 
-static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
-				    struct readdir_cd *cdp, loff_t *offsetp)
+static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
+				    nfsd_filldir_t func, struct readdir_cd *cdp,
+				    loff_t *offsetp)
 {
 	struct buffered_dirent *de;
 	int host_err;

@@ -2026,6 +2027,8 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 			if (cdp->err != nfs_ok)
 				break;
 
+			trace_nfsd_dirent(fhp, de->ino, de->name, de->namlen);
+
 			reclen = ALIGN(sizeof(*de) + de->namlen,
 				       sizeof(u64));
 			size -= reclen;

@@ -2073,7 +2076,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
 		goto out_close;
 	}
 
-	err = nfsd_buffered_readdir(file, func, cdp, offsetp);
+	err = nfsd_buffered_readdir(file, fhp, func, cdp, offsetp);
 
 	if (err == nfserr_eof || err == nfserr_toosmall)
 		err = nfs_ok; /* can still be found in ->err */

index fcfa0d611b931..0a5ebc52e6a9c 100644
@@ -14,9 +14,6 @@
 #include "netns.h"
 #include "vfs.h"
 
-#define NFSDDBG_FACILITY		NFSDDBG_XDR
-
-
 /*
  * Force construction of an empty post-op attr
  */

index b800cfefcab7a..a06c05fe3b421 100644
@@ -9,8 +9,6 @@
 #include "xdr.h"
 #include "auth.h"
 
-#define NFSDDBG_FACILITY		NFSDDBG_XDR
-
 /*
  * Mapping of S_IF* types to NFS file types
  */

index 914f60cee3226..0afc14b3e4593 100644
@@ -5385,6 +5385,22 @@ static bool clients_still_reclaiming(struct nfsd_net *nn)
 	return true;
 }
 
+struct laundry_time {
+	time64_t cutoff;
+	time64_t new_timeo;
+};
+
+static bool state_expired(struct laundry_time *lt, time64_t last_refresh)
+{
+	time64_t time_remaining;
+
+	if (last_refresh < lt->cutoff)
+		return true;
+	time_remaining = last_refresh - lt->cutoff;
+	lt->new_timeo = min(lt->new_timeo, time_remaining);
+	return false;
+}
+
 static time64_t
 nfs4_laundromat(struct nfsd_net *nn)
 {

@@ -5394,14 +5410,16 @@ nfs4_laundromat(struct nfsd_net *nn)
 	struct nfs4_ol_stateid *stp;
 	struct nfsd4_blocked_lock *nbl;
 	struct list_head *pos, *next, reaplist;
-	time64_t cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease;
-	time64_t t, new_timeo = nn->nfsd4_lease;
+	struct laundry_time lt = {
+		.cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease,
+		.new_timeo = nn->nfsd4_lease
+	};
 	struct nfs4_cpntf_state *cps;
 	copy_stateid_t *cps_t;
 	int i;
 
 	if (clients_still_reclaiming(nn)) {
-		new_timeo = 0;
+		lt.new_timeo = 0;
 		goto out;
 	}
 	nfsd4_end_grace(nn);

@@ -5411,7 +5429,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
 		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
 		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
-				cps->cpntf_time < cutoff)
+				state_expired(&lt, cps->cpntf_time))
 			_free_cpntf_state_locked(nn, cps);
 	}
 	spin_unlock(&nn->s2s_cp_lock);

@@ -5419,11 +5437,8 @@ nfs4_laundromat(struct nfsd_net *nn)
 	spin_lock(&nn->client_lock);
 	list_for_each_safe(pos, next, &nn->client_lru) {
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
-		if (clp->cl_time > cutoff) {
-			t = clp->cl_time - cutoff;
-			new_timeo = min(new_timeo, t);
+		if (!state_expired(&lt, clp->cl_time))
 			break;
-		}
 		if (mark_client_expired_locked(clp)) {
 			trace_nfsd_clid_expired(&clp->cl_clientid);
 			continue;

@@ -5440,11 +5455,8 @@ nfs4_laundromat(struct nfsd_net *nn)
 	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
-		if (dp->dl_time > cutoff) {
-			t = dp->dl_time - cutoff;
-			new_timeo = min(new_timeo, t);
+		if (!state_expired(&lt, dp->dl_time))
 			break;
-		}
 		WARN_ON(!unhash_delegation_locked(dp));
 		list_add(&dp->dl_recall_lru, &reaplist);
 	}

@@ -5460,11 +5472,8 @@ nfs4_laundromat(struct nfsd_net *nn)
 	while (!list_empty(&nn->close_lru)) {
 		oo = list_first_entry(&nn->close_lru, struct nfs4_openowner,
 					oo_close_lru);
-		if (oo->oo_time > cutoff) {
-			t = oo->oo_time - cutoff;
-			new_timeo = min(new_timeo, t);
+		if (!state_expired(&lt, oo->oo_time))
 			break;
-		}
 		list_del_init(&oo->oo_close_lru);
 		stp = oo->oo_last_closed_stid;
 		oo->oo_last_closed_stid = NULL;

@@ -5490,11 +5499,8 @@ nfs4_laundromat(struct nfsd_net *nn)
 	while (!list_empty(&nn->blocked_locks_lru)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
 					struct nfsd4_blocked_lock, nbl_lru);
-		if (nbl->nbl_time > cutoff) {
-			t = nbl->nbl_time - cutoff;
-			new_timeo = min(new_timeo, t);
+		if (!state_expired(&lt, nbl->nbl_time))
 			break;
-		}
 		list_move(&nbl->nbl_lru, &reaplist);
 		list_del_init(&nbl->nbl_list);
 	}

@@ -5507,8 +5513,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		free_blocked_lock(nbl);
 	}
 out:
-	new_timeo = max_t(time64_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
-	return new_timeo;
+	return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
 }
 
 static struct workqueue_struct *laundry_wq;

index 83c4e68839537..d08c1a8c9254b 100644
@@ -626,7 +626,7 @@ nfsd4_legacy_tracking_init(struct net *net)
 	status = nfsd4_load_reboot_recovery_data(net);
 	if (status)
 		goto err;
-	printk("NFSD: Using legacy client tracking operations.\n");
+	pr_info("NFSD: Using legacy client tracking operations.\n");
 	return 0;
 
 err:

@@ -1030,7 +1030,7 @@ nfsd4_init_cld_pipe(struct net *net)
 
 	status = __nfsd4_init_cld_pipe(net);
 	if (!status)
-		printk("NFSD: Using old nfsdcld client tracking operations.\n");
+		pr_info("NFSD: Using old nfsdcld client tracking operations.\n");
 	return status;
 }
 

@@ -1607,7 +1607,7 @@ nfsd4_cld_tracking_init(struct net *net)
 		nfs4_release_reclaim(nn);
 		goto err_remove;
 	} else
-		printk("NFSD: Using nfsdcld client tracking operations.\n");
+		pr_info("NFSD: Using nfsdcld client tracking operations.\n");
 	return 0;
 
 err_remove:

@@ -1866,7 +1866,7 @@ nfsd4_umh_cltrack_init(struct net *net)
 	ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL);
 	kfree(grace_start);
 	if (!ret)
-		printk("NFSD: Using UMH upcall client tracking operations.\n");
+		pr_info("NFSD: Using UMH upcall client tracking operations.\n");
 	return ret;
 }
 

index 2fba0808d975c..949d9cedef5d1 100644
@@ -1380,6 +1380,9 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
 	u64 src_pos = copy->cp_src_pos;
 	u64 dst_pos = copy->cp_dst_pos;
 
+	/* See RFC 7862 p.67: */
+	if (bytes_total == 0)
+		bytes_total = ULLONG_MAX;
 	do {
 		if (kthread_should_stop())
 			break;

index 949d9cedef5d1..f85958f81a266 100644
@@ -1376,7 +1376,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
 	struct file *dst = copy->nf_dst->nf_file;
 	struct file *src = copy->nf_src->nf_file;
 	ssize_t bytes_copied = 0;
-	size_t bytes_total = copy->cp_count;
+	u64 bytes_total = copy->cp_count;
 	u64 src_pos = copy->cp_src_pos;
 	u64 dst_pos = copy->cp_dst_pos;
 

index 0afc14b3e4593..104d563636540 100644
@@ -43,6 +43,7 @@
 #include <linux/sunrpc/addr.h>
 #include <linux/jhash.h>
 #include <linux/string_helpers.h>
+#include <linux/fsnotify.h>
 #include "xdr4.h"
 #include "xdr4cb.h"
 #include "vfs.h"

@@ -2370,6 +2371,10 @@ static int client_info_show(struct seq_file *m, void *v)
 	memcpy(&clid, &clp->cl_clientid, sizeof(clid));
 	seq_printf(m, "clientid: 0x%llx\n", clid);
 	seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr);
+	if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+		seq_puts(m, "status: confirmed\n");
+	else
+		seq_puts(m, "status: unconfirmed\n");
 	seq_printf(m, "name: ");
 	seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
 	seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);

@@ -2724,6 +2729,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 	int ret;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct dentry *dentries[ARRAY_SIZE(client_files)];
 
 	clp = alloc_client(name);
 	if (clp == NULL)

@@ -2743,9 +2749,11 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 	memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage));
 	clp->cl_cb_session = NULL;
 	clp->net = net;
-	clp->cl_nfsd_dentry = nfsd_client_mkdir(nn, &clp->cl_nfsdfs,
-			clp->cl_clientid.cl_id - nn->clientid_base,
-			client_files);
+	clp->cl_nfsd_dentry = nfsd_client_mkdir(
+		nn, &clp->cl_nfsdfs,
+		clp->cl_clientid.cl_id - nn->clientid_base,
+		client_files, dentries);
+	clp->cl_nfsd_info_dentry = dentries[0];
 	if (!clp->cl_nfsd_dentry) {
 		free_client(clp);
 		return NULL;

@@ -2820,7 +2828,10 @@ move_to_confirmed(struct nfs4_client *clp)
 	list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
 	rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
 	add_clp_to_name_tree(clp, &nn->conf_name_tree);
-	set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
+	if (!test_and_set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags) &&
+	    clp->cl_nfsd_dentry &&
+	    clp->cl_nfsd_info_dentry)
+		fsnotify_dentry(clp->cl_nfsd_info_dentry, FS_MODIFY);
 	renew_client_locked(clp);
 }
 

index fa060f91df1b8..147ed8995a79f 100644
@@ -1270,7 +1270,8 @@ static void nfsdfs_remove_files(struct dentry *root)
 /* XXX: cut'n'paste from simple_fill_super; figure out if we could share
  * code instead. */
 static  int nfsdfs_create_files(struct dentry *root,
-					const struct tree_descr *files)
+				const struct tree_descr *files,
+				struct dentry **fdentries)
 {
 	struct inode *dir = d_inode(root);
 	struct inode *inode;

@@ -1279,8 +1280,6 @@ static  int nfsdfs_create_files(struct dentry *root,
 
 	inode_lock(dir);
 	for (i = 0; files->name && files->name[0]; i++, files++) {
-		if (!files->name)
-			continue;
 		dentry = d_alloc_name(root, files->name);
 		if (!dentry)
 			goto out;

@@ -1294,6 +1293,8 @@ static  int nfsdfs_create_files(struct dentry *root,
 		inode->i_private = __get_nfsdfs_client(dir);
 		d_add(dentry, inode);
 		fsnotify_create(dir, dentry);
+		if (fdentries)
+			fdentries[i] = dentry;
 	}
 	inode_unlock(dir);
 	return 0;

@@ -1305,8 +1306,9 @@ static  int nfsdfs_create_files(struct dentry *root,
 
 /* on success, returns positive number unique to that client. */
 struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
-		struct nfsdfs_client *ncl, u32 id,
-		const struct tree_descr *files)
+				 struct nfsdfs_client *ncl, u32 id,
+				 const struct tree_descr *files,
+				 struct dentry **fdentries)
 {
 	struct dentry *dentry;
 	char name[11];

@@ -1317,7 +1319,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 	dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
 	if (IS_ERR(dentry)) /* XXX: tossing errors? */
 		return NULL;
-	ret = nfsdfs_create_files(dentry, files);
+	ret = nfsdfs_create_files(dentry, files, fdentries);
 	if (ret) {
 		nfsd_client_rmdir(dentry);
 		return NULL;

index 27c1308ffc2ba..14dbfa75059d5 100644
@@ -106,7 +106,9 @@ struct nfsdfs_client {
 
 struct nfsdfs_client *get_nfsdfs_client(struct inode *);
 struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
-		struct nfsdfs_client *ncl, u32 id, const struct tree_descr *);
+				 struct nfsdfs_client *ncl, u32 id,
+				 const struct tree_descr *,
+				 struct dentry **fdentries);
 void nfsd_client_rmdir(struct dentry *dentry);
 
 

index 73deea3531699..54cab651ac1d0 100644
@@ -371,6 +371,10 @@ struct nfs4_client {
 
 	/* debugging info directory under nfsd/clients/ : */
 	struct dentry		*cl_nfsd_dentry;
+	/* 'info' file within that directory. Ref is not counted,
+	 * but will remain valid iff cl_nfsd_dentry != NULL
+	 */
+	struct dentry		*cl_nfsd_info_dentry;
 
 	/* for nfs41 callbacks */
 	/* We currently support a single back channel with a single slot */

index 92455e0d52445..c5278871f9e40 100644
@@ -130,6 +130,7 @@ void	svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *,
 int	svc_create_xprt(struct svc_serv *, const char *, struct net *,
 			const int, const unsigned short, int,
 			const struct cred *);
+void	svc_xprt_received(struct svc_xprt *xprt);
 void	svc_xprt_do_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_put(struct svc_xprt *xprt);

index 200978b94a0b9..657138ab1f91f 100644
@@ -1756,6 +1756,7 @@ DECLARE_EVENT_CLASS(svc_xprt_event,
 			), \
 			TP_ARGS(xprt))
 
+DEFINE_SVC_XPRT_EVENT(received);
 DEFINE_SVC_XPRT_EVENT(no_write_space);
 DEFINE_SVC_XPRT_EVENT(close);
 DEFINE_SVC_XPRT_EVENT(detach);

index 06e503466c32c..d150e25b4d45e 100644
@@ -233,21 +233,25 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 	return xprt;
 }
 
-/*
- * svc_xprt_received conditionally queues the transport for processing
- * by another thread. The caller must hold the XPT_BUSY bit and must
+/**
+ * svc_xprt_received - start next receiver thread
+ * @xprt: controlling transport
+ *
+ * The caller must hold the XPT_BUSY bit and must
  * not thereafter touch transport data.
  *
  * Note: XPT_DATA only gets cleared when a read-attempt finds no (or
  * insufficient) data.
  */
-static void svc_xprt_received(struct svc_xprt *xprt)
+void svc_xprt_received(struct svc_xprt *xprt)
 {
 	if (!test_bit(XPT_BUSY, &xprt->xpt_flags)) {
 		WARN_ONCE(1, "xprt=0x%p already busy!", xprt);
 		return;
 	}
 
+	trace_svc_xprt_received(xprt);
+
 	/* As soon as we clear busy, the xprt could be closed and
 	 * 'put', so we need a reference to call svc_enqueue_xprt with:
 	 */

@@ -257,6 +261,7 @@ static void svc_xprt_received(struct svc_xprt *xprt)
 	xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt);
 	svc_xprt_put(xprt);
 }
+EXPORT_SYMBOL_GPL(svc_xprt_received);
 
 void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new)
 {

index ff0ca88b1c8f6..427294dd56a1b 100644
@@ -64,13 +64,24 @@ struct nfs_fhbase_old {
  *   in include/linux/exportfs.h for currently registered values.
  */
 struct nfs_fhbase_new {
-	__u8		fb_version;	/* == 1, even => nfs_fhbase_old */
-	__u8		fb_auth_type;
-	__u8		fb_fsid_type;
-	__u8		fb_fileid_type;
-	__u32		fb_auth[1];
-/*	__u32		fb_fsid[0]; floating */
-/*	__u32		fb_fileid[0]; floating */
+	union {
+		struct {
+			__u8		fb_version_aux;	/* == 1, even => nfs_fhbase_old */
+			__u8		fb_auth_type_aux;
+			__u8		fb_fsid_type_aux;
+			__u8		fb_fileid_type_aux;
+			__u32		fb_auth[1];
+			/*	__u32		fb_fsid[0]; floating */
+			/*	__u32		fb_fileid[0]; floating */
+		};
+		struct {
+			__u8		fb_version;	/* == 1, even => nfs_fhbase_old */
+			__u8		fb_auth_type;
+			__u8		fb_fsid_type;
+			__u8		fb_fileid_type;
+			__u32		fb_auth_flex[]; /* flexible-array member */
+		};
+	};
 };
 
 struct knfsd_fh {

@@ -97,7 +108,7 @@ struct knfsd_fh {
 #define	fh_fsid_type		fh_base.fh_new.fb_fsid_type
 #define	fh_auth_type		fh_base.fh_new.fb_auth_type
 #define	fh_fileid_type		fh_base.fh_new.fb_fileid_type
-#define	fh_fsid			fh_base.fh_new.fb_auth
+#define	fh_fsid			fh_base.fh_new.fb_auth_flex
 
 /* Do not use, provided for userspace compatiblity. */
 #define	fh_auth			fh_base.fh_new.fb_auth

index 0666ef4b87b7a..79bc75d415226 100644
@@ -84,7 +84,7 @@ DEFINE_MUTEX(nfsd_mutex);
  * version 4.1 DRC caches.
  * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
  */
-spinlock_t	nfsd_drc_lock;
+DEFINE_SPINLOCK(nfsd_drc_lock);
 unsigned long	nfsd_drc_max_mem;
 unsigned long	nfsd_drc_mem_used;
 

@@ -563,7 +563,6 @@ static void set_max_drc(void)
 	nfsd_drc_max_mem = (nr_free_buffer_pages()
 					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
 	nfsd_drc_mem_used = 0;
-	spin_lock_init(&nfsd_drc_lock);
 	dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
 }
 

index 829ead2792dfb..30651e8d1a6d5 100644
@@ -100,24 +100,30 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 {
 	size_t event_size = FAN_EVENT_METADATA_LEN;
 	struct fanotify_event *event = NULL;
+	struct fsnotify_event *fsn_event;
 	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
 
 	pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
 
 	spin_lock(&group->notification_lock);
-	if (fsnotify_notify_queue_is_empty(group))
+	fsn_event = fsnotify_peek_first_event(group);
+	if (!fsn_event)
 		goto out;
 
-	if (fid_mode) {
-		event_size += fanotify_event_info_len(fid_mode,
-			FANOTIFY_E(fsnotify_peek_first_event(group)));
-	}
+	event = FANOTIFY_E(fsn_event);
+	if (fid_mode)
+		event_size += fanotify_event_info_len(fid_mode, event);
 
 	if (event_size > count) {
 		event = ERR_PTR(-EINVAL);
 		goto out;
 	}
-	event = FANOTIFY_E(fsnotify_remove_first_event(group));
+
+	/*
+	 * Held the notification_lock the whole time, so this is the
+	 * same event we peeked above.
+	 */
+	fsnotify_remove_first_event(group);
 	if (fanotify_is_perm_event(event->mask))
 		FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
 out:

@@ -573,6 +579,7 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t
 static int fanotify_release(struct inode *ignored, struct file *file)
 {
 	struct fsnotify_group *group = file->private_data;
+	struct fsnotify_event *fsn_event;
 
 	/*
 	 * Stop new events from arriving in the notification queue. since

@@ -601,13 +608,12 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	 * dequeue them and set the response. They will be freed once the
 	 * response is consumed and fanotify_get_response() returns.
 	 */
-	while (!fsnotify_notify_queue_is_empty(group)) {
-		struct fanotify_event *event;
+	while ((fsn_event = fsnotify_remove_first_event(group))) {
+		struct fanotify_event *event = FANOTIFY_E(fsn_event);
 
-		event = FANOTIFY_E(fsnotify_remove_first_event(group));
 		if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
 			spin_unlock(&group->notification_lock);
-			fsnotify_destroy_event(group, &event->fse);
+			fsnotify_destroy_event(group, fsn_event);
 		} else {
 			finish_permission_event(group, FANOTIFY_PERM(event),
 						FAN_ALLOW);

index 82fc0cf86a7c3..c2018983832e5 100644
@@ -146,10 +146,9 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 	size_t event_size = sizeof(struct inotify_event);
 	struct fsnotify_event *event;
 
-	if (fsnotify_notify_queue_is_empty(group))
-		return NULL;
-
 	event = fsnotify_peek_first_event(group);
+	if (!event)
+		return NULL;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 

65 lines not on this page · raw message

index e5409b83e7313..7eb979bfc1413 100644
@@ -495,7 +495,13 @@ static inline void fsnotify_queue_overflow(struct fsnotify_group *group)
 	fsnotify_add_event(group, group->overflow_event, NULL);
 }
 
-/* true if the group notification queue is empty */
+static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)
+{
+	assert_spin_locked(&group->notification_lock);
+
+	return list_empty(&group->notification_list);
+}
+
 extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 /* return, but do not dequeue the first event on the notification queue */
 extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group);

index c3af99e94f1d1..1192c99536200 100644
@@ -129,15 +129,11 @@ static bool fanotify_should_merge(struct fsnotify_event *old_fsn,
 	return false;
 }
 
-/* Limit event merges to limit CPU overhead per event */
-#define FANOTIFY_MAX_MERGE_EVENTS 128
-
 /* and the list better be locked by something too! */
 static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 {
 	struct fsnotify_event *test_event;
 	struct fanotify_event *new;
-	int i = 0;
 
 	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
 	new = FANOTIFY_E(event);

@@ -151,8 +147,6 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 		return 0;
 
 	list_for_each_entry_reverse(test_event, list, list) {
-		if (++i > FANOTIFY_MAX_MERGE_EVENTS)
-			break;
 		if (fanotify_should_merge(test_event, event)) {
 			FANOTIFY_E(test_event)->mask |= new->mask;
 			return 1;

index 1192c99536200..8a2bb6954e02c 100644
@@ -88,16 +88,12 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
 	return fanotify_info_equal(info1, info2);
 }
 
-static bool fanotify_should_merge(struct fsnotify_event *old_fsn,
-				  struct fsnotify_event *new_fsn)
+static bool fanotify_should_merge(struct fanotify_event *old,
+				  struct fanotify_event *new)
 {
-	struct fanotify_event *old, *new;
+	pr_debug("%s: old=%p new=%p\n", __func__, old, new);
 
-	pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
-	old = FANOTIFY_E(old_fsn);
-	new = FANOTIFY_E(new_fsn);
-
-	if (old_fsn->objectid != new_fsn->objectid ||
+	if (old->hash != new->hash ||
 	    old->type != new->type || old->pid != new->pid)
 		return false;
 

@@ -133,10 +129,9 @@ static bool fanotify_should_merge(struct fsnotify_event *old_fsn,
 static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 {
 	struct fsnotify_event *test_event;
-	struct fanotify_event *new;
+	struct fanotify_event *old, *new = FANOTIFY_E(event);
 
 	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
-	new = FANOTIFY_E(event);
 
 	/*
 	 * Don't merge a permission event with any other event so that we know

@@ -147,8 +142,9 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 		return 0;
 
 	list_for_each_entry_reverse(test_event, list, list) {
-		if (fanotify_should_merge(test_event, event)) {
-			FANOTIFY_E(test_event)->mask |= new->mask;
+		old = FANOTIFY_E(test_event);
+		if (fanotify_should_merge(old, new)) {
+			old->mask |= new->mask;
 			return 1;
 		}
 	}

@@ -533,6 +529,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	struct mem_cgroup *old_memcg;
 	struct inode *child = NULL;
 	bool name_event = false;
+	unsigned int hash = 0;
 
 	if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
 		/*

@@ -600,8 +597,10 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	 * Use the victim inode instead of the watching inode as the id for
 	 * event queue, so event reported on parent is merged with event
 	 * reported on child when both directory and child watches exist.
+	 * Hash object id for queue merge.
 	 */
-	fanotify_init_event(event, (unsigned long)id, mask);
+	hash = hash_ptr(id, FANOTIFY_EVENT_HASH_BITS);
+	fanotify_init_event(event, hash, mask);
 	if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
 		event->pid = get_pid(task_pid(current));
 	else

index 896c819a17863..d531f0cfa46f2 100644
@@ -135,19 +135,29 @@ enum fanotify_event_type {
 	FANOTIFY_EVENT_TYPE_PATH,
 	FANOTIFY_EVENT_TYPE_PATH_PERM,
 	FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+	__FANOTIFY_EVENT_TYPE_NUM
 };
 
+#define FANOTIFY_EVENT_TYPE_BITS \
+	(ilog2(__FANOTIFY_EVENT_TYPE_NUM - 1) + 1)
+#define FANOTIFY_EVENT_HASH_BITS \
+	(32 - FANOTIFY_EVENT_TYPE_BITS)
+
 struct fanotify_event {
 	struct fsnotify_event fse;
 	u32 mask;
-	enum fanotify_event_type type;
+	struct {
+		unsigned int type : FANOTIFY_EVENT_TYPE_BITS;
+		unsigned int hash : FANOTIFY_EVENT_HASH_BITS;
+	};
 	struct pid *pid;
 };
 
 static inline void fanotify_init_event(struct fanotify_event *event,
-				       unsigned long id, u32 mask)
+				       unsigned int hash, u32 mask)
 {
-	fsnotify_init_event(&event->fse, id);
+	fsnotify_init_event(&event->fse);
+	event->hash = hash;
 	event->mask = mask;
 	event->pid = NULL;
 }

index 66991c7fef9e2..e2b124c0081dc 100644
@@ -114,7 +114,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 		mask &= ~IN_ISDIR;
 
 	fsn_event = &event->fse;
-	fsnotify_init_event(fsn_event, 0);
+	fsnotify_init_event(fsn_event);
 	event->mask = mask;
 	event->wd = wd;
 	event->sync_cookie = cookie;

index c2018983832e5..62cd91bc00b83 100644
@@ -641,7 +641,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 		return ERR_PTR(-ENOMEM);
 	}
 	group->overflow_event = &oevent->fse;
-	fsnotify_init_event(group->overflow_event, 0);
+	fsnotify_init_event(group->overflow_event);
 	oevent->mask = FS_Q_OVERFLOW;
 	oevent->wd = -1;
 	oevent->sync_cookie = 0;

index 7eb979bfc1413..fc98f9f88d126 100644
@@ -167,7 +167,6 @@ struct fsnotify_ops {
  */
 struct fsnotify_event {
 	struct list_head list;
-	unsigned long objectid;	/* identifier for queue merges */
 };
 
 /*

@@ -582,11 +581,9 @@ extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
 extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
 
-static inline void fsnotify_init_event(struct fsnotify_event *event,
-				       unsigned long objectid)
+static inline void fsnotify_init_event(struct fsnotify_event *event)
 {
 	INIT_LIST_HEAD(&event->list);
-	event->objectid = objectid;
 }
 
 #else

index 8a2bb6954e02c..43a606f153702 100644
@@ -14,6 +14,7 @@
 #include <linux/audit.h>
 #include <linux/sched/mm.h>
 #include <linux/statfs.h>
+#include <linux/stringhash.h>
 
 #include "fanotify.h"
 

@@ -22,12 +23,24 @@ static bool fanotify_path_equal(struct path *p1, struct path *p2)
 	return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
 }
 
+static unsigned int fanotify_hash_path(const struct path *path)
+{
+	return hash_ptr(path->dentry, FANOTIFY_EVENT_HASH_BITS) ^
+		hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
+}
+
 static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
 				       __kernel_fsid_t *fsid2)
 {
 	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
 }
 
+static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
+{
+	return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
+		hash_32(fsid->val[1], FANOTIFY_EVENT_HASH_BITS);
+}
+
 static bool fanotify_fh_equal(struct fanotify_fh *fh1,
 			      struct fanotify_fh *fh2)
 {

@@ -38,6 +51,16 @@ static bool fanotify_fh_equal(struct fanotify_fh *fh1,
 		!memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
 }
 
+static unsigned int fanotify_hash_fh(struct fanotify_fh *fh)
+{
+	long salt = (long)fh->type | (long)fh->len << 8;
+
+	/*
+	 * full_name_hash() works long by long, so it handles fh buf optimally.
+	 */
+	return full_name_hash((void *)salt, fanotify_fh_buf(fh), fh->len);
+}
+
 static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
 				     struct fanotify_fid_event *ffe2)
 {

@@ -325,7 +348,8 @@ static int fanotify_encode_fh_len(struct inode *inode)
  * Return 0 on failure to encode.
  */
 static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
-			      unsigned int fh_len, gfp_t gfp)
+			      unsigned int fh_len, unsigned int *hash,
+			      gfp_t gfp)
 {
 	int dwords, type = 0;
 	char *ext_buf = NULL;

@@ -368,6 +392,9 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
 	fh->type = type;
 	fh->len = fh_len;
 
+	/* Mix fh into event merge key */
+	*hash ^= fanotify_hash_fh(fh);
+
 	return FANOTIFY_FH_HDR_LEN + fh_len;
 
 out_err:

@@ -421,6 +448,7 @@ static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
 }
 
 static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
+							unsigned int *hash,
 							gfp_t gfp)
 {
 	struct fanotify_path_event *pevent;

@@ -431,6 +459,7 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
 
 	pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH;
 	pevent->path = *path;
+	*hash ^= fanotify_hash_path(path);
 	path_get(path);
 
 	return &pevent->fae;

@@ -456,6 +485,7 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
 
 static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
 						       __kernel_fsid_t *fsid,
+						       unsigned int *hash,
 						       gfp_t gfp)
 {
 	struct fanotify_fid_event *ffe;

@@ -466,16 +496,18 @@ static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
 
 	ffe->fae.type = FANOTIFY_EVENT_TYPE_FID;
 	ffe->fsid = *fsid;
+	*hash ^= fanotify_hash_fsid(fsid);
 	fanotify_encode_fh(&ffe->object_fh, id, fanotify_encode_fh_len(id),
-			   gfp);
+			   hash, gfp);
 
 	return &ffe->fae;
 }
 
 static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
 							__kernel_fsid_t *fsid,
-							const struct qstr *file_name,
+							const struct qstr *name,
 							struct inode *child,
+							unsigned int *hash,
 							gfp_t gfp)
 {
 	struct fanotify_name_event *fne;

@@ -488,24 +520,30 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
 	size = sizeof(*fne) + FANOTIFY_FH_HDR_LEN + dir_fh_len;
 	if (child_fh_len)
 		size += FANOTIFY_FH_HDR_LEN + child_fh_len;
-	if (file_name)
-		size += file_name->len + 1;
+	if (name)
+		size += name->len + 1;
 	fne = kmalloc(size, gfp);
 	if (!fne)
 		return NULL;
 
 	fne->fae.type = FANOTIFY_EVENT_TYPE_FID_NAME;
 	fne->fsid = *fsid;
+	*hash ^= fanotify_hash_fsid(fsid);
 	info = &fne->info;
 	fanotify_info_init(info);
 	dfh = fanotify_info_dir_fh(info);
-	info->dir_fh_totlen = fanotify_encode_fh(dfh, id, dir_fh_len, 0);
+	info->dir_fh_totlen = fanotify_encode_fh(dfh, id, dir_fh_len, hash, 0);
 	if (child_fh_len) {
 		ffh = fanotify_info_file_fh(info);
-		info->file_fh_totlen = fanotify_encode_fh(ffh, child, child_fh_len, 0);
+		info->file_fh_totlen = fanotify_encode_fh(ffh, child,
+							child_fh_len, hash, 0);
+	}
+	if (name) {
+		long salt = name->len;
+
+		fanotify_info_copy_name(info, name);
+		*hash ^= full_name_hash((void *)salt, name->name, name->len);
 	}
-	if (file_name)
-		fanotify_info_copy_name(info, file_name);
 
 	pr_debug("%s: ino=%lu size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n",
 		 __func__, id->i_ino, size, dir_fh_len, child_fh_len,

@@ -530,6 +568,8 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	struct inode *child = NULL;
 	bool name_event = false;
 	unsigned int hash = 0;
+	bool ondir = mask & FAN_ONDIR;
+	struct pid *pid;
 
 	if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
 		/*

@@ -537,8 +577,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		 * report the child fid for events reported on a non-dir child
 		 * in addition to reporting the parent fid and maybe child name.
 		 */
-		if ((fid_mode & FAN_REPORT_FID) &&
-		    id != dirid && !(mask & FAN_ONDIR))
+		if ((fid_mode & FAN_REPORT_FID) && id != dirid && !ondir)
 			child = id;
 
 		id = dirid;

@@ -559,8 +598,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		if (!(fid_mode & FAN_REPORT_NAME)) {
 			name_event = !!child;
 			file_name = NULL;
-		} else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
-			   !(mask & FAN_ONDIR)) {
+		} else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) {
 			name_event = true;
 		}
 	}

@@ -583,28 +621,25 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		event = fanotify_alloc_perm_event(path, gfp);
 	} else if (name_event && (file_name || child)) {
 		event = fanotify_alloc_name_event(id, fsid, file_name, child,
-						  gfp);
+						  &hash, gfp);
 	} else if (fid_mode) {
-		event = fanotify_alloc_fid_event(id, fsid, gfp);
+		event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
 	} else {
-		event = fanotify_alloc_path_event(path, gfp);
+		event = fanotify_alloc_path_event(path, &hash, gfp);
 	}
 
 	if (!event)
 		goto out;
 
-	/*
-	 * Use the victim inode instead of the watching inode as the id for
-	 * event queue, so event reported on parent is merged with event
-	 * reported on child when both directory and child watches exist.
-	 * Hash object id for queue merge.
-	 */
-	hash = hash_ptr(id, FANOTIFY_EVENT_HASH_BITS);
-	fanotify_init_event(event, hash, mask);
 	if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
-		event->pid = get_pid(task_pid(current));
+		pid = get_pid(task_pid(current));
 	else
-		event->pid = get_pid(task_tgid(current));
+		pid = get_pid(task_tgid(current));
+
+	/* Mix event info, FAN_ONDIR flag and pid into event merge key */
+	hash ^= hash_long((unsigned long)pid | ondir, FANOTIFY_EVENT_HASH_BITS);
+	fanotify_init_event(event, hash, mask);
+	event->pid = pid;
 
 out:
 	set_active_memcg(old_memcg);

index d531f0cfa46f2..9871f76cd9c2c 100644
@@ -115,6 +115,11 @@ static inline void fanotify_info_init(struct fanotify_info *info)
 	info->name_len = 0;
 }
 
+static inline unsigned int fanotify_info_len(struct fanotify_info *info)
+{
+	return info->dir_fh_totlen + info->file_fh_totlen + info->name_len;
+}
+
 static inline void fanotify_info_copy_name(struct fanotify_info *info,
 					   const struct qstr *name)
 {

index 43a606f153702..50b3abc062156 100644
@@ -149,12 +149,15 @@ static bool fanotify_should_merge(struct fanotify_event *old,
 }
 
 /* and the list better be locked by something too! */
-static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
+static int fanotify_merge(struct fsnotify_group *group,
+			  struct fsnotify_event *event)
 {
-	struct fsnotify_event *test_event;
 	struct fanotify_event *old, *new = FANOTIFY_E(event);
+	unsigned int bucket = fanotify_event_hash_bucket(group, new);
+	struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
 
-	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
+	pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+		 group, event, bucket);
 
 	/*
 	 * Don't merge a permission event with any other event so that we know

@@ -164,8 +167,7 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 	if (fanotify_is_perm_event(new->mask))
 		return 0;
 
-	list_for_each_entry_reverse(test_event, list, list) {
-		old = FANOTIFY_E(test_event);
+	hlist_for_each_entry(old, hlist, merge_list) {
 		if (fanotify_should_merge(old, new)) {
 			old->mask |= new->mask;
 			return 1;

@@ -203,8 +205,11 @@ static int fanotify_get_response(struct fsnotify_group *group,
 			return ret;
 		}
 		/* Event not yet reported? Just remove it. */
-		if (event->state == FAN_EVENT_INIT)
+		if (event->state == FAN_EVENT_INIT) {
 			fsnotify_remove_queued_event(group, &event->fae.fse);
+			/* Permission events are not supposed to be hashed */
+			WARN_ON_ONCE(!hlist_unhashed(&event->fae.merge_list));
+		}
 		/*
 		 * Event may be also answered in case signal delivery raced
 		 * with wakeup. In that case we have nothing to do besides

@@ -679,6 +684,24 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	return fsid;
 }
 
+/*
+ * Add an event to hash table for faster merge.
+ */
+static void fanotify_insert_event(struct fsnotify_group *group,
+				  struct fsnotify_event *fsn_event)
+{
+	struct fanotify_event *event = FANOTIFY_E(fsn_event);
+	unsigned int bucket = fanotify_event_hash_bucket(group, event);
+	struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+
+	assert_spin_locked(&group->notification_lock);
+
+	pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+		 group, event, bucket);
+
+	hlist_add_head(&event->merge_list, hlist);
+}
+
 static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 				 const void *data, int data_type,
 				 struct inode *dir,

@@ -749,7 +772,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	}
 
 	fsn_event = &event->fse;
-	ret = fsnotify_add_event(group, fsn_event, fanotify_merge);
+	ret = fsnotify_add_event(group, fsn_event, fanotify_merge,
+				 fanotify_is_hashed_event(mask) ?
+				 fanotify_insert_event : NULL);
 	if (ret) {
 		/* Permission events shouldn't be merged */
 		BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);

@@ -772,6 +797,7 @@ static void fanotify_free_group_priv(struct fsnotify_group *group)
 {
 	struct user_struct *user;
 
+	kfree(group->fanotify_data.merge_hash);
 	user = group->fanotify_data.user;
 	atomic_dec(&user->fanotify_listeners);
 	free_uid(user);

index 9871f76cd9c2c..4a5e555dc3d25 100644
@@ -3,6 +3,7 @@
 #include <linux/path.h>
 #include <linux/slab.h>
 #include <linux/exportfs.h>
+#include <linux/hashtable.h>
 
 extern struct kmem_cache *fanotify_mark_cache;
 extern struct kmem_cache *fanotify_fid_event_cachep;

@@ -150,6 +151,7 @@ enum fanotify_event_type {
 
 struct fanotify_event {
 	struct fsnotify_event fse;
+	struct hlist_node merge_list;	/* List for hashed merge */
 	u32 mask;
 	struct {
 		unsigned int type : FANOTIFY_EVENT_TYPE_BITS;

@@ -162,6 +164,7 @@ static inline void fanotify_init_event(struct fanotify_event *event,
 				       unsigned int hash, u32 mask)
 {
 	fsnotify_init_event(&event->fse);
+	INIT_HLIST_NODE(&event->merge_list);
 	event->hash = hash;
 	event->mask = mask;
 	event->pid = NULL;

@@ -299,3 +302,25 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event)
 	else
 		return NULL;
 }
+
+/*
+ * Use 128 size hash table to speed up events merge.
+ */
+#define FANOTIFY_HTABLE_BITS	(7)
+#define FANOTIFY_HTABLE_SIZE	(1 << FANOTIFY_HTABLE_BITS)
+#define FANOTIFY_HTABLE_MASK	(FANOTIFY_HTABLE_SIZE - 1)
+
+/*
+ * Permission events and overflow event do not get merged - don't hash them.
+ */
+static inline bool fanotify_is_hashed_event(u32 mask)
+{
+	return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW);
+}
+
+static inline unsigned int fanotify_event_hash_bucket(
+						struct fsnotify_group *group,
+						struct fanotify_event *event)
+{
+	return event->hash & FANOTIFY_HTABLE_MASK;
+}

index 30651e8d1a6d5..1456470d0c4c6 100644
@@ -89,6 +89,23 @@ static int fanotify_event_info_len(unsigned int fid_mode,
 	return info_len;
 }
 
+/*
+ * Remove an hashed event from merge hash table.
+ */
+static void fanotify_unhash_event(struct fsnotify_group *group,
+				  struct fanotify_event *event)
+{
+	assert_spin_locked(&group->notification_lock);
+
+	pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+		 group, event, fanotify_event_hash_bucket(group, event));
+
+	if (WARN_ON_ONCE(hlist_unhashed(&event->merge_list)))
+		return;
+
+	hlist_del_init(&event->merge_list);
+}
+
 /*
  * Get an fanotify notification event if one exists and is small
  * enough to fit in "count". Return an error pointer if the count

@@ -126,6 +143,8 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 	fsnotify_remove_first_event(group);
 	if (fanotify_is_perm_event(event->mask))
 		FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
+	if (fanotify_is_hashed_event(event->mask))
+		fanotify_unhash_event(group, event);
 out:
 	spin_unlock(&group->notification_lock);
 	return event;

@@ -925,6 +944,20 @@ static struct fsnotify_event *fanotify_alloc_overflow_event(void)
 	return &oevent->fse;
 }
 
+static struct hlist_head *fanotify_alloc_merge_hash(void)
+{
+	struct hlist_head *hash;
+
+	hash = kmalloc(sizeof(struct hlist_head) << FANOTIFY_HTABLE_BITS,
+		       GFP_KERNEL_ACCOUNT);
+	if (!hash)
+		return NULL;
+
+	__hash_init(hash, FANOTIFY_HTABLE_SIZE);
+
+	return hash;
+}
+
 /* fanotify syscalls */
 SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 {

@@ -993,6 +1026,12 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	atomic_inc(&user->fanotify_listeners);
 	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
+	group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
+	if (!group->fanotify_data.merge_hash) {
+		fd = -ENOMEM;
+		goto out_destroy_group;
+	}
+
 	group->overflow_event = fanotify_alloc_overflow_event();
 	if (unlikely(!group->overflow_event)) {
 		fd = -ENOMEM;

index e2b124c0081dc..b0530f75b274a 100644
@@ -46,9 +46,10 @@ static bool event_compare(struct fsnotify_event *old_fsn,
 	return false;
 }
 
-static int inotify_merge(struct list_head *list,
-			  struct fsnotify_event *event)
+static int inotify_merge(struct fsnotify_group *group,
+			 struct fsnotify_event *event)
 {
+	struct list_head *list = &group->notification_list;
 	struct fsnotify_event *last_event;
 
 	last_event = list_entry(list->prev, struct fsnotify_event, list);

@@ -122,7 +123,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 	if (len)
 		strcpy(event->name, name->name);
 
-	ret = fsnotify_add_event(group, fsn_event, inotify_merge);
+	ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL);
 	if (ret) {
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);

index 001cfe7d2e4e7..32f45543b9c64 100644
@@ -68,16 +68,22 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
 }
 
 /*
- * Add an event to the group notification queue.  The group can later pull this
- * event off the queue to deal with.  The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event,
+ * Try to add an event to the notification queue.
+ * The group can later pull this event off the queue to deal with.
+ * The group can use the @merge hook to merge the event with a queued event.
+ * The group can use the @insert hook to insert the event into hash table.
+ * The function returns:
+ * 0 if the event was added to a queue
+ * 1 if the event was merged with some other queued event
  * 2 if the event was not queued - either the queue of events has overflown
- * or the group is shutting down.
+ *   or the group is shutting down.
  */
 int fsnotify_add_event(struct fsnotify_group *group,
 		       struct fsnotify_event *event,
-		       int (*merge)(struct list_head *,
-				    struct fsnotify_event *))
+		       int (*merge)(struct fsnotify_group *,
+				    struct fsnotify_event *),
+		       void (*insert)(struct fsnotify_group *,
+				      struct fsnotify_event *))
 {
 	int ret = 0;
 	struct list_head *list = &group->notification_list;

@@ -104,7 +110,7 @@ int fsnotify_add_event(struct fsnotify_group *group,
 	}
 
 	if (!list_empty(list) && merge) {
-		ret = merge(list, event);
+		ret = merge(group, event);
 		if (ret) {
 			spin_unlock(&group->notification_lock);
 			return ret;

@@ -114,6 +120,8 @@ int fsnotify_add_event(struct fsnotify_group *group,
 queue:
 	group->q_len++;
 	list_add_tail(&event->list, list);
+	if (insert)
+		insert(group, event);
 	spin_unlock(&group->notification_lock);
 
 	wake_up(&group->notification_waitq);

index fc98f9f88d126..63fb766f0f3ec 100644
@@ -233,6 +233,8 @@ struct fsnotify_group {
 #endif
 #ifdef CONFIG_FANOTIFY
 		struct fanotify_group_private_data {
+			/* Hash table of events for merge */
+			struct hlist_head *merge_hash;
 			/* allows a group to block waiting for a userspace response */
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;

@@ -486,12 +488,14 @@ extern void fsnotify_destroy_event(struct fsnotify_group *group,
 /* attach the event to the group notification queue */
 extern int fsnotify_add_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
-			      int (*merge)(struct list_head *,
-					   struct fsnotify_event *));
+			      int (*merge)(struct fsnotify_group *,
+					   struct fsnotify_event *),
+			      void (*insert)(struct fsnotify_group *,
+					     struct fsnotify_event *));
 /* Queue overflow event to a notification group */
 static inline void fsnotify_queue_overflow(struct fsnotify_group *group)
 {
-	fsnotify_add_event(group, group->overflow_event, NULL);
+	fsnotify_add_event(group, group->overflow_event, NULL, NULL);
 }
 
 static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)

index 50b3abc062156..754e27ead8742 100644
@@ -148,6 +148,9 @@ static bool fanotify_should_merge(struct fanotify_event *old,
 	return false;
 }
 
+/* Limit event merges to limit CPU overhead per event */
+#define FANOTIFY_MAX_MERGE_EVENTS 128
+
 /* and the list better be locked by something too! */
 static int fanotify_merge(struct fsnotify_group *group,
 			  struct fsnotify_event *event)

@@ -155,6 +158,7 @@ static int fanotify_merge(struct fsnotify_group *group,
 	struct fanotify_event *old, *new = FANOTIFY_E(event);
 	unsigned int bucket = fanotify_event_hash_bucket(group, new);
 	struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+	int i = 0;
 
 	pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
 		 group, event, bucket);

@@ -168,6 +172,8 @@ static int fanotify_merge(struct fsnotify_group *group,
 		return 0;
 
 	hlist_for_each_entry(old, hlist, merge_list) {
+		if (++i > FANOTIFY_MAX_MERGE_EVENTS)
+			break;
 		if (fanotify_should_merge(old, new)) {
 			old->mask |= new->mask;
 			return 1;

index 754e27ead8742..057abd2cf8875 100644
@@ -801,12 +801,10 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 
 static void fanotify_free_group_priv(struct fsnotify_group *group)
 {
-	struct user_struct *user;
-
 	kfree(group->fanotify_data.merge_hash);
-	user = group->fanotify_data.user;
-	atomic_dec(&user->fanotify_listeners);
-	free_uid(user);
+	if (group->fanotify_data.ucounts)
+		dec_ucount(group->fanotify_data.ucounts,
+			   UCOUNT_FANOTIFY_GROUPS);
 }
 
 static void fanotify_free_path_event(struct fanotify_event *event)

@@ -862,6 +860,13 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
 	}
 }
 
+static void fanotify_freeing_mark(struct fsnotify_mark *mark,
+				  struct fsnotify_group *group)
+{
+	if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+		dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_MARKS);
+}
+
 static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
 {
 	kmem_cache_free(fanotify_mark_cache, fsn_mark);

@@ -871,5 +876,6 @@ const struct fsnotify_ops fanotify_fsnotify_ops = {
 	.handle_event = fanotify_handle_event,
 	.free_group_priv = fanotify_free_group_priv,
 	.free_event = fanotify_free_event,
+	.freeing_mark = fanotify_freeing_mark,
 	.free_mark = fanotify_free_mark,
 };

195 lines not on this page · raw message

index ffd723ffe46de..fb89c351295d6 100644
@@ -122,7 +122,6 @@ static struct fsnotify_group *__fsnotify_alloc_group(
 
 	/* set to 0 when there a no external references to this group */
 	refcount_set(&group->refcnt, 1);
-	atomic_set(&group->num_marks, 0);
 	atomic_set(&group->user_waits, 0);
 
 	spin_lock_init(&group->notification_lock);

index 5b44be5f93dd8..7af98a7c33c27 100644
@@ -391,8 +391,6 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
 	list_del_init(&mark->g_list);
 	spin_unlock(&mark->lock);
 
-	atomic_dec(&group->num_marks);
-
 	/* Drop mark reference acquired in fsnotify_add_mark_locked() */
 	fsnotify_put_mark(mark);
 }

@@ -656,7 +654,6 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
 
 	list_add(&mark->g_list, &group->marks_list);
-	atomic_inc(&group->num_marks);
 	fsnotify_get_mark(mark); /* for g_list */
 	spin_unlock(&mark->lock);
 

@@ -674,7 +671,6 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 			 FSNOTIFY_MARK_FLAG_ATTACHED);
 	list_del_init(&mark->g_list);
 	spin_unlock(&mark->lock);
-	atomic_dec(&group->num_marks);
 
 	fsnotify_put_mark(mark);
 	return ret;

index 3e9c56ee651f7..031a97d8369ae 100644
@@ -2,8 +2,11 @@
 #ifndef _LINUX_FANOTIFY_H
 #define _LINUX_FANOTIFY_H
 
+#include <linux/sysctl.h>
 #include <uapi/linux/fanotify.h>
 
+extern struct ctl_table fanotify_table[]; /* for sysctl */
+
 #define FAN_GROUP_FLAG(group, flag) \
 	((group)->fanotify_data.flags & (flag))
 

index 63fb766f0f3ec..1ce66748a2d29 100644
@@ -206,9 +206,6 @@ struct fsnotify_group {
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	struct mutex mark_mutex;	/* protect marks_list */
-	atomic_t num_marks;		/* 1 for each mark and 1 for not being
-					 * past the point of no return when freeing
-					 * a group */
 	atomic_t user_waits;		/* Number of tasks waiting for user
 					 * response */
 	struct list_head marks_list;	/* all inode marks for this group */

@@ -240,8 +237,7 @@ struct fsnotify_group {
 			wait_queue_head_t access_waitq;
 			int flags;           /* flags from fanotify_init() */
 			int f_flags; /* event_f_flags from fanotify_init() */
-			unsigned int max_marks;
-			struct user_struct *user;
+			struct ucounts *ucounts;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};

index a8ec3b6093fcb..3632c5d6ec559 100644
@@ -14,9 +14,6 @@ struct user_struct {
 	refcount_t __count;	/* reference count */
 	atomic_t processes;	/* How many processes does this user have? */
 	atomic_t sigpending;	/* How many pending signals does this user have? */
-#ifdef CONFIG_FANOTIFY
-	atomic_t fanotify_listeners;
-#endif
 #ifdef CONFIG_EPOLL
 	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
 #endif

index 7616c7bf4b241..0793951867aef 100644
@@ -49,6 +49,10 @@ enum ucount_type {
 #ifdef CONFIG_INOTIFY_USER
 	UCOUNT_INOTIFY_INSTANCES,
 	UCOUNT_INOTIFY_WATCHES,
+#endif
+#ifdef CONFIG_FANOTIFY
+	UCOUNT_FANOTIFY_GROUPS,
+	UCOUNT_FANOTIFY_MARKS,
 #endif
 	UCOUNT_COUNTS,
 };

index 99a19190196e0..b29a9568ebbe4 100644
@@ -142,6 +142,9 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
 #ifdef CONFIG_INOTIFY_USER
 #include <linux/inotify.h>
 #endif
+#ifdef CONFIG_FANOTIFY
+#include <linux/fanotify.h>
+#endif
 
 #ifdef CONFIG_PROC_SYSCTL
 

@@ -3330,7 +3333,14 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0555,
 		.child		= inotify_table,
 	},
-#endif	
+#endif
+#ifdef CONFIG_FANOTIFY
+	{
+		.procname	= "fanotify",
+		.mode		= 0555,
+		.child		= fanotify_table,
+	},
+#endif
 #ifdef CONFIG_EPOLL
 	{
 		.procname	= "epoll",

index 11b1596e2542a..8d8874f1c35e2 100644
@@ -73,6 +73,10 @@ static struct ctl_table user_table[] = {
 #ifdef CONFIG_INOTIFY_USER
 	UCOUNT_ENTRY("max_inotify_instances"),
 	UCOUNT_ENTRY("max_inotify_watches"),
+#endif
+#ifdef CONFIG_FANOTIFY
+	UCOUNT_ENTRY("max_fanotify_groups"),
+	UCOUNT_ENTRY("max_fanotify_marks"),
 #endif
 	{ }
 };

index 74b4da6354e1c..842cccb4f7499 100644
@@ -419,6 +419,14 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	metadata.reserved = 0;
 	metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
 	metadata.pid = pid_vnr(event->pid);
+	/*
+	 * For an unprivileged listener, event->pid can be used to identify the
+	 * events generated by the listener process itself, without disclosing
+	 * the pids of other processes.
+	 */
+	if (!capable(CAP_SYS_ADMIN) &&
+	    task_tgid(current) != event->pid)
+		metadata.pid = 0;
 
 	if (path && path->mnt && path->dentry) {
 		fd = create_fd(group, path, &f);

@@ -1036,8 +1044,16 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	pr_debug("%s: flags=%x event_f_flags=%x\n",
 		 __func__, flags, event_f_flags);
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (!capable(CAP_SYS_ADMIN)) {
+		/*
+		 * An unprivileged user can setup an fanotify group with
+		 * limited functionality - an unprivileged group is limited to
+		 * notification events with file handles and it cannot use
+		 * unlimited queue/marks.
+		 */
+		if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
+			return -EPERM;
+	}
 
 #ifdef CONFIG_AUDITSYSCALL
 	if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))

@@ -1306,6 +1322,15 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 		goto fput_and_out;
 	group = f.file->private_data;
 
+	/*
+	 * An unprivileged user is not allowed to watch a mount point nor
+	 * a filesystem.
+	 */
+	ret = -EPERM;
+	if (!capable(CAP_SYS_ADMIN) &&
+	    mark_type != FAN_MARK_INODE)
+		goto fput_and_out;
+
 	/*
 	 * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF.  These are not
 	 * allowed to set permissions events.

index 765b50aeadd28..85b112bd88511 100644
@@ -137,7 +137,8 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
 	struct fsnotify_group *group = f->private_data;
 
 	seq_printf(m, "fanotify flags:%x event-flags:%x\n",
-		   group->fanotify_data.flags, group->fanotify_data.f_flags);
+		   group->fanotify_data.flags,
+		   group->fanotify_data.f_flags);
 
 	show_fdinfo(m, f, fanotify_fdinfo);
 }

index 031a97d8369ae..bad41bcb25dfb 100644
@@ -18,15 +18,38 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
  * these constant, the programs may break if re-compiled with new uapi headers
  * and then run on an old kernel.
  */
-#define FANOTIFY_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
+
+/* Group classes where permission events are allowed */
+#define FANOTIFY_PERM_CLASSES	(FAN_CLASS_CONTENT | \
 				 FAN_CLASS_PRE_CONTENT)
 
+#define FANOTIFY_CLASS_BITS	(FAN_CLASS_NOTIF | FANOTIFY_PERM_CLASSES)
+
 #define FANOTIFY_FID_BITS	(FAN_REPORT_FID | FAN_REPORT_DFID_NAME)
 
-#define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \
-				 FAN_REPORT_TID | \
-				 FAN_CLOEXEC | FAN_NONBLOCK | \
-				 FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS)
+/*
+ * fanotify_init() flags that require CAP_SYS_ADMIN.
+ * We do not allow unprivileged groups to request permission events.
+ * We do not allow unprivileged groups to get other process pid in events.
+ * We do not allow unprivileged groups to use unlimited resources.
+ */
+#define FANOTIFY_ADMIN_INIT_FLAGS	(FANOTIFY_PERM_CLASSES | \
+					 FAN_REPORT_TID | \
+					 FAN_UNLIMITED_QUEUE | \
+					 FAN_UNLIMITED_MARKS)
+
+/*
+ * fanotify_init() flags that are allowed for user without CAP_SYS_ADMIN.
+ * FAN_CLASS_NOTIF is the only class we allow for unprivileged group.
+ * We do not allow unprivileged groups to get file descriptors in events,
+ * so one of the flags for reporting file handles is required.
+ */
+#define FANOTIFY_USER_INIT_FLAGS	(FAN_CLASS_NOTIF | \
+					 FANOTIFY_FID_BITS | \
+					 FAN_CLOEXEC | FAN_NONBLOCK)
+
+#define FANOTIFY_INIT_FLAGS	(FANOTIFY_ADMIN_INIT_FLAGS | \
+				 FANOTIFY_USER_INIT_FLAGS)
 
 #define FANOTIFY_MARK_TYPE_BITS	(FAN_MARK_INODE | FAN_MARK_MOUNT | \
 				 FAN_MARK_FILESYSTEM)

index 842cccb4f7499..98289ace66fac 100644
@@ -1268,7 +1268,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 		 __func__, fanotify_fd, flags, dfd, pathname, mask);
 
 	/* we only use the lower 32 bits as of right now. */
-	if (mask & ((__u64)0xffffffff << 32))
+	if (upper_32_bits(mask))
 		return -EINVAL;
 
 	if (flags & ~FANOTIFY_MARK_FLAGS)

index 104d563636540..a42a505b3e417 100644
@@ -6336,15 +6336,6 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
-static inline u64
-end_offset(u64 start, u64 len)
-{
-	u64 end;
-
-	end = start + len;
-	return end >= start ? end: NFS4_MAX_UINT64;
-}
-
 /* last octet in a range */
 static inline u64
 last_byte_offset(u64 start, u64 len)

index 79bc75d415226..731d89898903a 100644
@@ -308,7 +308,7 @@ static int nfsd_init_socks(struct net *net, const struct cred *cred)
 
 static int nfsd_users = 0;
 
-static int nfsd_startup_generic(int nrservs)
+static int nfsd_startup_generic(void)
 {
 	int ret;
 

@@ -374,7 +374,7 @@ void nfsd_reset_boot_verifier(struct nfsd_net *nn)
 	write_sequnlock(&nn->boot_lock);
 }
 
-static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cred)
+static int nfsd_startup_net(struct net *net, const struct cred *cred)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	int ret;

@@ -382,7 +382,7 @@ static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cre
 	if (nn->nfsd_net_up)
 		return 0;
 
-	ret = nfsd_startup_generic(nrservs);
+	ret = nfsd_startup_generic();
 	if (ret)
 		return ret;
 	ret = nfsd_init_socks(net, cred);

@@ -790,7 +790,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 
 	nfsd_up_before = nn->nfsd_net_up;
 
-	error = nfsd_startup_net(nrservs, net, cred);
+	error = nfsd_startup_net(net, cred);
 	if (error)
 		goto out_destroy;
 	error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv,

index a42a505b3e417..8d2d6e90bfc5e 100644
@@ -554,14 +554,12 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername)
 #define FILE_HASH_BITS                   8
 #define FILE_HASH_SIZE                  (1 << FILE_HASH_BITS)
 
-static unsigned int nfsd_fh_hashval(struct knfsd_fh *fh)
+static unsigned int file_hashval(struct svc_fh *fh)
 {
-	return jhash2(fh->fh_base.fh_pad, XDR_QUADLEN(fh->fh_size), 0);
-}
+	struct inode *inode = d_inode(fh->fh_dentry);
 
-static unsigned int file_hashval(struct knfsd_fh *fh)
-{
-	return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1);
+	/* XXX: why not (here & in file cache) use inode? */
+	return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS);
 }
 
 static struct hlist_head file_hashtbl[FILE_HASH_SIZE];

@@ -4106,7 +4104,7 @@ static struct nfs4_file *nfsd4_alloc_file(void)
 }
 
 /* OPEN Share state helper functions */
-static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
+static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval,
 				struct nfs4_file *fp)
 {
 	lockdep_assert_held(&state_lock);

@@ -4116,7 +4114,7 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 	INIT_LIST_HEAD(&fp->fi_stateids);
 	INIT_LIST_HEAD(&fp->fi_delegations);
 	INIT_LIST_HEAD(&fp->fi_clnt_odstate);
-	fh_copy_shallow(&fp->fi_fhandle, fh);
+	fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle);
 	fp->fi_deleg_file = NULL;
 	fp->fi_had_conflict = false;
 	fp->fi_share_deny = 0;

@@ -4460,13 +4458,13 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
 
 /* search file_hashtbl[] for file */
 static struct nfs4_file *
-find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
+find_file_locked(struct svc_fh *fh, unsigned int hashval)
 {
 	struct nfs4_file *fp;
 
 	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
 				lockdep_is_held(&state_lock)) {
-		if (fh_match(&fp->fi_fhandle, fh)) {
+		if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) {
 			if (refcount_inc_not_zero(&fp->fi_ref))
 				return fp;
 		}

@@ -4474,8 +4472,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	return NULL;
 }
 
-struct nfs4_file *
-find_file(struct knfsd_fh *fh)
+static struct nfs4_file * find_file(struct svc_fh *fh)
 {
 	struct nfs4_file *fp;
 	unsigned int hashval = file_hashval(fh);

@@ -4487,7 +4484,7 @@ find_file(struct knfsd_fh *fh)
 }
 
 static struct nfs4_file *
-find_or_add_file(struct nfs4_file *new, struct knfsd_fh *fh)
+find_or_add_file(struct nfs4_file *new, struct svc_fh *fh)
 {
 	struct nfs4_file *fp;
 	unsigned int hashval = file_hashval(fh);

@@ -4519,7 +4516,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	struct nfs4_file *fp;
 	__be32 ret = nfs_ok;
 
-	fp = find_file(&current_fh->fh_handle);
+	fp = find_file(current_fh);
 	if (!fp)
 		return ret;
 	/* Check for conflicting share reservations */

@@ -5208,7 +5205,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	 * and check for delegations in the process of being recalled.
 	 * If not found, create the nfs4_file struct
 	 */
-	fp = find_or_add_file(open->op_file, &current_fh->fh_handle);
+	fp = find_or_add_file(open->op_file, current_fh);
 	if (fp != open->op_file) {
 		status = nfs4_check_deleg(cl, open, &dp);
 		if (status)

index 54cab651ac1d0..61a2d95d79233 100644
@@ -669,7 +669,6 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name
 				struct xdr_netobj princhash, struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
 
-struct nfs4_file *find_file(struct knfsd_fh *fh);
 void put_nfs4_file(struct nfs4_file *fi);
 extern void nfs4_put_copy(struct nfsd4_copy *copy);
 extern struct nfsd4_copy *

index 8d2d6e90bfc5e..89d5669ce1463 100644
@@ -4120,6 +4120,8 @@ static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval,
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
+	fp->fi_aliased = false;
+	fp->fi_inode = d_inode(fh->fh_dentry);
 #ifdef CONFIG_NFSD_PNFS
 	INIT_LIST_HEAD(&fp->fi_lo_states);
 	atomic_set(&fp->fi_lo_recalls, 0);

@@ -4472,6 +4474,31 @@ find_file_locked(struct svc_fh *fh, unsigned int hashval)
 	return NULL;
 }
 
+static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh,
+				     unsigned int hashval)
+{
+	struct nfs4_file *fp;
+	struct nfs4_file *ret = NULL;
+	bool alias_found = false;
+
+	spin_lock(&state_lock);
+	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
+				 lockdep_is_held(&state_lock)) {
+		if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) {
+			if (refcount_inc_not_zero(&fp->fi_ref))
+				ret = fp;
+		} else if (d_inode(fh->fh_dentry) == fp->fi_inode)
+			fp->fi_aliased = alias_found = true;
+	}
+	if (likely(ret == NULL)) {
+		nfsd4_init_file(fh, hashval, new);
+		new->fi_aliased = alias_found;
+		ret = new;
+	}
+	spin_unlock(&state_lock);
+	return ret;
+}
+
 static struct nfs4_file * find_file(struct svc_fh *fh)
 {
 	struct nfs4_file *fp;

@@ -4495,15 +4522,7 @@ find_or_add_file(struct nfs4_file *new, struct svc_fh *fh)
 	if (fp)
 		return fp;
 
-	spin_lock(&state_lock);
-	fp = find_file_locked(fh, hashval);
-	if (likely(fp == NULL)) {
-		nfsd4_init_file(fh, hashval, new);
-		fp = new;
-	}
-	spin_unlock(&state_lock);
-
-	return fp;
+	return insert_file(new, fh, hashval);
 }
 
 /*

index 61a2d95d79233..e73bdbb1634ab 100644
@@ -516,6 +516,8 @@ struct nfs4_clnt_odstate {
  */
 struct nfs4_file {
 	refcount_t		fi_ref;
+	struct inode *		fi_inode;
+	bool			fi_aliased;
 	spinlock_t		fi_lock;
 	struct hlist_node       fi_hash;	/* hash on fi_fhandle */
 	struct list_head        fi_stateids;

index 89d5669ce1463..9c8dacf0f2b86 100644
@@ -354,6 +354,124 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
 	.release	= nfsd4_cb_notify_lock_release,
 };
 
+/*
+ * We store the NONE, READ, WRITE, and BOTH bits separately in the
+ * st_{access,deny}_bmap field of the stateid, in order to track not
+ * only what share bits are currently in force, but also what
+ * combinations of share bits previous opens have used.  This allows us
+ * to enforce the recommendation of rfc 3530 14.2.19 that the server
+ * return an error if the client attempt to downgrade to a combination
+ * of share bits not explicable by closing some of its previous opens.
+ *
+ * XXX: This enforcement is actually incomplete, since we don't keep
+ * track of access/deny bit combinations; so, e.g., we allow:
+ *
+ *	OPEN allow read, deny write
+ *	OPEN allow both, deny none
+ *	DOWNGRADE allow read, deny none
+ *
+ * which we should reject.
+ */
+static unsigned int
+bmap_to_share_mode(unsigned long bmap)
+{
+	int i;
+	unsigned int access = 0;
+
+	for (i = 1; i < 4; i++) {
+		if (test_bit(i, &bmap))
+			access |= i;
+	}
+	return access;
+}
+
+/* set share access for a given stateid */
+static inline void
+set_access(u32 access, struct nfs4_ol_stateid *stp)
+{
+	unsigned char mask = 1 << access;
+
+	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
+	stp->st_access_bmap |= mask;
+}
+
+/* clear share access for a given stateid */
+static inline void
+clear_access(u32 access, struct nfs4_ol_stateid *stp)
+{
+	unsigned char mask = 1 << access;
+
+	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
+	stp->st_access_bmap &= ~mask;
+}
+
+/* test whether a given stateid has access */
+static inline bool
+test_access(u32 access, struct nfs4_ol_stateid *stp)
+{
+	unsigned char mask = 1 << access;
+
+	return (bool)(stp->st_access_bmap & mask);
+}
+
+/* set share deny for a given stateid */
+static inline void
+set_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+	unsigned char mask = 1 << deny;
+
+	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
+	stp->st_deny_bmap |= mask;
+}
+
+/* clear share deny for a given stateid */
+static inline void
+clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+	unsigned char mask = 1 << deny;
+
+	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
+	stp->st_deny_bmap &= ~mask;
+}
+
+/* test whether a given stateid is denying specific access */
+static inline bool
+test_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+	unsigned char mask = 1 << deny;
+
+	return (bool)(stp->st_deny_bmap & mask);
+}
+
+static int nfs4_access_to_omode(u32 access)
+{
+	switch (access & NFS4_SHARE_ACCESS_BOTH) {
+	case NFS4_SHARE_ACCESS_READ:
+		return O_RDONLY;
+	case NFS4_SHARE_ACCESS_WRITE:
+		return O_WRONLY;
+	case NFS4_SHARE_ACCESS_BOTH:
+		return O_RDWR;
+	}
+	WARN_ON_ONCE(1);
+	return O_RDONLY;
+}
+
+static inline int
+access_permit_read(struct nfs4_ol_stateid *stp)
+{
+	return test_access(NFS4_SHARE_ACCESS_READ, stp) ||
+		test_access(NFS4_SHARE_ACCESS_BOTH, stp) ||
+		test_access(NFS4_SHARE_ACCESS_WRITE, stp);
+}
+
+static inline int
+access_permit_write(struct nfs4_ol_stateid *stp)
+{
+	return test_access(NFS4_SHARE_ACCESS_WRITE, stp) ||
+		test_access(NFS4_SHARE_ACCESS_BOTH, stp);
+}
+
 static inline struct nfs4_stateowner *
 nfs4_get_stateowner(struct nfs4_stateowner *sop)
 {

@@ -1167,108 +1285,6 @@ static unsigned int clientstr_hashval(struct xdr_netobj name)
 	return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK;
 }
 
-/*
- * We store the NONE, READ, WRITE, and BOTH bits separately in the
- * st_{access,deny}_bmap field of the stateid, in order to track not
- * only what share bits are currently in force, but also what
- * combinations of share bits previous opens have used.  This allows us
- * to enforce the recommendation of rfc 3530 14.2.19 that the server
- * return an error if the client attempt to downgrade to a combination
- * of share bits not explicable by closing some of its previous opens.
- *
- * XXX: This enforcement is actually incomplete, since we don't keep
- * track of access/deny bit combinations; so, e.g., we allow:
- *
- *	OPEN allow read, deny write
- *	OPEN allow both, deny none
- *	DOWNGRADE allow read, deny none
- *
- * which we should reject.
- */
-static unsigned int
-bmap_to_share_mode(unsigned long bmap) {
-	int i;
-	unsigned int access = 0;
-
-	for (i = 1; i < 4; i++) {
-		if (test_bit(i, &bmap))
-			access |= i;
-	}
-	return access;
-}
-
-/* set share access for a given stateid */
-static inline void
-set_access(u32 access, struct nfs4_ol_stateid *stp)
-{
-	unsigned char mask = 1 << access;
-
-	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
-	stp->st_access_bmap |= mask;
-}
-
-/* clear share access for a given stateid */
-static inline void
-clear_access(u32 access, struct nfs4_ol_stateid *stp)
-{
-	unsigned char mask = 1 << access;
-
-	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
-	stp->st_access_bmap &= ~mask;
-}
-
-/* test whether a given stateid has access */
-static inline bool
-test_access(u32 access, struct nfs4_ol_stateid *stp)
-{
-	unsigned char mask = 1 << access;
-
-	return (bool)(stp->st_access_bmap & mask);
-}
-
-/* set share deny for a given stateid */
-static inline void
-set_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
-	unsigned char mask = 1 << deny;
-
-	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
-	stp->st_deny_bmap |= mask;
-}
-
-/* clear share deny for a given stateid */
-static inline void
-clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
-	unsigned char mask = 1 << deny;
-
-	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
-	stp->st_deny_bmap &= ~mask;
-}
-
-/* test whether a given stateid is denying specific access */
-static inline bool
-test_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
-	unsigned char mask = 1 << deny;
-
-	return (bool)(stp->st_deny_bmap & mask);
-}
-
-static int nfs4_access_to_omode(u32 access)
-{
-	switch (access & NFS4_SHARE_ACCESS_BOTH) {
-	case NFS4_SHARE_ACCESS_READ:
-		return O_RDONLY;
-	case NFS4_SHARE_ACCESS_WRITE:
-		return O_WRONLY;
-	case NFS4_SHARE_ACCESS_BOTH:
-		return O_RDWR;
-	}
-	WARN_ON_ONCE(1);
-	return O_RDONLY;
-}
-
 /*
  * A stateid that had a deny mode associated with it is being released
  * or downgraded. Recalculate the deny mode on the file.

@@ -5565,21 +5581,6 @@ static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 	return nfs_ok;
 }
 
-static inline int
-access_permit_read(struct nfs4_ol_stateid *stp)
-{
-	return test_access(NFS4_SHARE_ACCESS_READ, stp) ||
-		test_access(NFS4_SHARE_ACCESS_BOTH, stp) ||
-		test_access(NFS4_SHARE_ACCESS_WRITE, stp);
-}
-
-static inline int
-access_permit_write(struct nfs4_ol_stateid *stp)
-{
-	return test_access(NFS4_SHARE_ACCESS_WRITE, stp) ||
-		test_access(NFS4_SHARE_ACCESS_BOTH, stp);
-}
-
 static
 __be32 nfs4_check_openmode(struct nfs4_ol_stateid *stp, int flags)
 {

index 873f97504bddf..101867933e4d3 100644
@@ -1808,6 +1808,9 @@ check_conflicting_open(struct file *filp, const long arg, int flags)
 
 	if (flags & FL_LAYOUT)
 		return 0;
+	if (flags & FL_DELEG)
+		/* We leave these checks to the caller */
+		return 0;
 
 	if (arg == F_RDLCK)
 		return inode_is_open_for_write(inode) ? -EAGAIN : 0;

106 lines not on this page · raw message

index fd0d6e81a2272..ea68dc157ada1 100644
@@ -3161,6 +3161,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			goto out_nolock;
 		}
 		new->cl_mach_cred = true;
+		break;
 	case SP4_NONE:
 		break;
 	default:				/* checked by xdr code */

index 147ed8995a79f..cb73c12925629 100644
@@ -1169,6 +1169,7 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
 		inode->i_fop = &simple_dir_operations;
 		inode->i_op = &simple_dir_inode_operations;
 		inc_nlink(inode);
+		break;
 	default:
 		break;
 	}

index 5ad57ad89fb1e..70cd0d764c447 100644
@@ -430,9 +430,7 @@ static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = {
  */
 void nfs42_ssc_register_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl);
-#endif
 }
 
 /**

@@ -443,9 +441,7 @@ void nfs42_ssc_register_ops(void)
  */
 void nfs42_ssc_unregister_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl);
-#endif
 }
 #endif /* CONFIG_NFS_V4_2 */
 

index 7179d59d73ca4..1ffce90760606 100644
@@ -116,16 +116,12 @@ static void unregister_nfs4_fs(void)
 #ifdef CONFIG_NFS_V4_2
 static void nfs_ssc_register_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs_ssc_register(&nfs_ssc_clnt_ops_tbl);
-#endif
 }
 
 static void nfs_ssc_unregister_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs_ssc_unregister(&nfs_ssc_clnt_ops_tbl);
-#endif
 }
 #endif /* CONFIG_NFS_V4_2 */