[src/netbsd-9]: src/sys Pull up following revision(s) (requested by dholland ...

[martin <martin%NetBSD.org@localhost>]

details:   https://anonhg.NetBSD.org/src/rev/fb1a39fc7a52
branches:  netbsd-9
changeset: 1002298:fb1a39fc7a52
user:      martin <martin%NetBSD.org@localhost>
date:      Mon Jun 21 14:50:57 2021 +0000

description:
Pull up following revision(s) (requested by dholland in ticket #1296):

        sys/sys/namei.src: revision 1.59        (via patch)
        sys/kern/vfs_vnops.c: revision 1.215
        sys/kern/vfs_lookup.c: revision 1.226

Add a new namei flag NONEXCLHACK for open with O_CREAT and not O_EXCL.
This case needs to be distinguished from the other CREATE operations
because it is supposed to successfully return (and open) the target if
it exists. In the case where that target is the root, or a mount
point, such that there's no parent dir, "real" CREATE operations fail,
but O_CREAT without O_EXCL needs to succeed.

So (a) add the flag, (b) test for it in namei in the situation
described above, (c) set it in open under the appropriate
circumstances, and (d) because this can result in namei returning
ni_dvp of NULL, cope with that case.

Should get into -9 and maybe even -8, because it was prompted by
issues with 3rd-party code. The use of a flag (vs. adding an
additional nameiop, which would be more appropriate) was deliberate to
make the patch small and noninvasive.

diffstat:

 sys/kern/vfs_lookup.c |  29 ++++++++++++++++++++++++++---
 sys/kern/vfs_vnops.c  |  29 +++++++++++++++++++++++++----
 sys/sys/namei.src     |   5 +++--
 3 files changed, 54 insertions(+), 9 deletions(-)

diffs (143 lines):

diff -r 03830afcdf85 -r fb1a39fc7a52 sys/kern/vfs_lookup.c
--- a/sys/kern/vfs_lookup.c     Mon Jun 14 12:00:44 2021 +0000
+++ b/sys/kern/vfs_lookup.c     Mon Jun 21 14:50:57 2021 +0000
@@ -1,4 +1,4 @@
-/*     $NetBSD: vfs_lookup.c,v 1.212 2019/07/18 09:39:40 hannken Exp $ */
+/*     $NetBSD: vfs_lookup.c,v 1.212.2.1 2021/06/21 14:50:57 martin Exp $      */
 
 /*
  * Copyright (c) 1982, 1986, 1989, 1993
@@ -37,7 +37,7 @@
  */
 
 #include <sys/cdefs.h>
-__KERNEL_RCSID(0, "$NetBSD: vfs_lookup.c,v 1.212 2019/07/18 09:39:40 hannken Exp $");
+__KERNEL_RCSID(0, "$NetBSD: vfs_lookup.c,v 1.212.2.1 2021/06/21 14:50:57 martin Exp $");
 
 #ifdef _KERNEL_OPT
 #include "opt_magiclinks.h"
@@ -1434,10 +1434,33 @@
                 * a CREATE, DELETE, or RENAME), and we don't have one
                 * (because this is the root directory, or we crossed
                 * a mount point), then we must fail.
+                *
+                * 20210604 dholland when NONEXCLHACK is set (open
+                * with O_CREAT but not O_EXCL) skip this logic. Since
+                * we have a foundobj, open will not be creating, so
+                * it doesn't actually need or use the searchdir, so
+                * it's ok to return it even if it's on a different
+                * volume, and it's also ok to return NULL; by setting
+                * NONEXCLHACK the open code promises to cope with
+                * those cases correctly. (That is, it should do what
+                * it would do anyway, that is, just release the
+                * searchdir, except not crash if it's null.) This is
+                * needed because otherwise opening mountpoints with
+                * O_CREAT but not O_EXCL fails... which is a silly
+                * thing to do but ought to work. (This whole issue
+                * came to light because 3rd party code wanted to open
+                * certain procfs nodes with O_CREAT for some 3rd
+                * party reason, and it failed.)
+                *
+                * Note that NONEXCLHACK is properly a different
+                * nameiop (it is partway between LOOKUP and CREATE)
+                * but it was stuffed in as a flag instead to make the
+                * resulting patch less invasive for pullup. Blah.
                 */
                if (cnp->cn_nameiop != LOOKUP &&
                    (searchdir == NULL ||
-                    searchdir->v_mount != foundobj->v_mount)) {
+                    searchdir->v_mount != foundobj->v_mount) &&
+                   (cnp->cn_flags & NONEXCLHACK) == 0) {
                        if (searchdir) {
                                vput(searchdir);
                        }
diff -r 03830afcdf85 -r fb1a39fc7a52 sys/kern/vfs_vnops.c
--- a/sys/kern/vfs_vnops.c      Mon Jun 14 12:00:44 2021 +0000
+++ b/sys/kern/vfs_vnops.c      Mon Jun 21 14:50:57 2021 +0000
@@ -1,4 +1,4 @@
-/*     $NetBSD: vfs_vnops.c,v 1.200 2019/03/07 11:09:48 hannken Exp $  */
+/*     $NetBSD: vfs_vnops.c,v 1.200.4.1 2021/06/21 14:50:57 martin Exp $       */
 
 /*-
  * Copyright (c) 2009 The NetBSD Foundation, Inc.
@@ -66,7 +66,7 @@
  */
 
 #include <sys/cdefs.h>
-__KERNEL_RCSID(0, "$NetBSD: vfs_vnops.c,v 1.200 2019/03/07 11:09:48 hannken Exp $");
+__KERNEL_RCSID(0, "$NetBSD: vfs_vnops.c,v 1.200.4.1 2021/06/21 14:50:57 martin Exp $");
 
 #include "veriexec.h"
 
@@ -161,6 +161,8 @@
                if ((fmode & O_EXCL) == 0 &&
                    ((fmode & O_NOFOLLOW) == 0))
                        ndp->ni_cnd.cn_flags |= FOLLOW;
+               if ((fmode & O_EXCL) == 0)
+                       ndp->ni_cnd.cn_flags |= NONEXCLHACK;
        } else {
                ndp->ni_cnd.cn_nameiop = LOOKUP;
                ndp->ni_cnd.cn_flags |= LOCKLEAF;
@@ -183,7 +185,12 @@
        error = veriexec_openchk(l, ndp->ni_vp, pathstring, fmode);
        if (error) {
                /* We have to release the locks ourselves */
-               if (fmode & O_CREAT) {
+               /*
+                * 20210604 dholland passing NONEXCLHACK means we can
+                * get ni_dvp == NULL back if ni_vp exists, and we should
+                * treat that like the non-O_CREAT case.
+                */
+               if ((fmode & O_CREAT) != 0 && ndp->ni_dvp != NULL) {
                        if (vp == NULL) {
                                vput(ndp->ni_dvp);
                        } else {
@@ -202,7 +209,10 @@
        }
 #endif /* NVERIEXEC > 0 */
 
-       if (fmode & O_CREAT) {
+       /*
+        * 20210604 dholland ditto
+        */
+       if ((fmode & O_CREAT) != 0 && ndp->ni_dvp != NULL) {
                if (ndp->ni_vp == NULL) {
                        vattr_null(&va);
                        va.va_type = VREG;
@@ -233,6 +243,17 @@
                        }
                        fmode &= ~O_CREAT;
                }
+       } else if ((fmode & O_CREAT) != 0) {
+               /*
+                * 20210606 dholland passing NONEXCLHACK means this
+                * case exists; it is the same as the following one
+                * but also needs to do things in the second (exists)
+                * half of the following block. (Besides handle
+                * ni_dvp, anyway.)
+                */
+               vp = ndp->ni_vp;
+               KASSERT((fmode & O_EXCL) == 0);
+               fmode &= ~O_CREAT;
        } else {
                vp = ndp->ni_vp;
        }
diff -r 03830afcdf85 -r fb1a39fc7a52 sys/sys/namei.src
--- a/sys/sys/namei.src Mon Jun 14 12:00:44 2021 +0000
+++ b/sys/sys/namei.src Mon Jun 21 14:50:57 2021 +0000
@@ -1,4 +1,4 @@
-/*     $NetBSD: namei.src,v 1.42 2019/06/03 06:04:21 msaitoh Exp $     */
+/*     $NetBSD: namei.src,v 1.42.2.1 2021/06/21 14:50:57 martin Exp $  */
 
 /*
  * Copyright (c) 1985, 1989, 1991, 1993
@@ -152,7 +152,8 @@
 NAMEIFL        EMULROOTSET     0x00000080      /* emulation root already
                                           in ni_erootdir */
 NAMEIFL        NOCHROOT        0x01000000      /* no chroot on abs path lookups */
-NAMEIFL        MODMASK         0x010000fc      /* mask of operational modifiers */
+NAMEIFL        NONEXCLHACK     0x02000000      /* open wwith O_CREAT but not O_EXCL */
+NAMEIFL        MODMASK         0x030000fc      /* mask of operational modifiers */
 /*
  * Namei parameter descriptors.
  */