- 14 Nov, 2012 1 commit
-
-
Jan Beulich authored
Header length should be validated for all ACPI tables before accessing any non-header field. Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/509A9E6002000078000A7079@nat28.tlf.novell.comAcked-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
-
- 13 Nov, 2012 1 commit
-
-
Matt Fleming authored
We don't want someone who can write EFI variables to be able to allocate arbitrarily large amounts of memory, so cap it to something sensible like the amount of free space for EFI variables. Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Cc: Matthew Garrett <mjg@redhat.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
- 30 Oct, 2012 21 commits
-
-
Matt Fleming authored
We're stuffing a variable of type size_t (unsigned) into a ssize_t (signed) which, even though both types should be the same number of bits, it's just asking for sign issues to be introduced. Cc: Jeremy Kerr <jeremy.kerr@canonical.com> Reported-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
Instead of returning -ENOSPC if efivarfs_get_inode() fails we should be returning -ENOMEM, since running out of memory is the only reason it can fail. Furthermore, that's the error value used everywhere else in this file. It's also less likely to confuse users that hit this error case. Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
There's no reason to declare 'datasize' as an int, since the majority of the functions it's passed to expect an unsigned long anyway. Plus, this way we avoid any sign problems during arithmetic. Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
Using pstore's superblock magic number is no doubt going to cause problems in the future. Give efivarfs its own magic number. Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
Seeing "+ 4" littered throughout the functions gets a bit confusing. Use "sizeof(attributes)" which clearly explains what quantity we're adding. Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
Instead of always returning 0 in efivarfs_file_read(), even when we fail to successfully read the variable, convert the EFI status to something meaningful and return that to the caller. This way the user will have some hint as to why the read failed. Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Jeremy Kerr authored
At present, the handling of GUIDs in efivar file names isn't consistent. We use GUID_LEN in some places, and 38 in others (GUID_LEN plus separator), and implicitly use the presence of the trailing NUL. This change removes the trailing NUL from GUID_LEN, so that we're explicitly adding it when required. We also replace magic numbers with GUID_LEN, and clarify the comments where appropriate. We also fix the allocation size in efivar_create_sysfs_entry, where we're allocating one byte too much, due to counting the trailing NUL twice - once when calculating short_name_size, and once in the kzalloc. Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Jeremy Kerr authored
Currently, efivarfs does not enforce exclusion over the get_variable and set_variable operations. Section 7.1 of UEFI requires us to only allow a single processor to enter {get,set}_variable services at once. This change acquires the efivars->lock over calls to these operations from the efivarfs paths. Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Andy Whitcroft authored
Ensure we free both the name and inode on error when building the individual variables. Signed-off-by: Andy Whitcroft <apw@canonical.com> Acked-by: Matthew Garrett <mjg@redhat.com> Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Andy Whitcroft authored
d_alloc_name() copies the passed name to new storage, once complete we no longer need our name. Signed-off-by: Andy Whitcroft <apw@canonical.com> Acked-by: Matthew Garrett <mjg@redhat.com> Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Andy Whitcroft authored
When d_make_root() fails it will automatically drop the reference on the root inode. We should not be doing so as well. Signed-off-by: Andy Whitcroft <apw@canonical.com> Acked-by: Matthew Garrett <mjg@redhat.com> Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Andy Whitcroft authored
Signed-off-by: Andy Whitcroft <apw@canonical.com> Acked-by: Matthew Garrett <mjg@redhat.com> Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Andy Whitcroft authored
Signed-off-by: Andy Whitcroft <apw@canonical.com> Acked-by: Matthew Garrett <mjg@redhat.com> Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Jan Beulich authored
Other than ix86, x86-64 on EFI so far didn't set the {g,s}et_wallclock accessors to the EFI routines, thus incorrectly using raw RTC accesses instead. Simply removing the #ifdef around the respective code isn't enough, however: While so far early get-time calls were done in physical mode, this doesn't work properly for x86-64, as virtual addresses would still need to be set up for all runtime regions (which wasn't the case on the system I have access to), so instead the patch moves the call to efi_enter_virtual_mode() ahead (which in turn allows to drop all code related to calling efi-get-time in physical mode). Additionally the earlier calling of efi_set_executable() requires the CPA code to cope, i.e. during early boot it must be avoided to call cpa_flush_array(), as the first thing this function does is a BUG_ON(irqs_disabled()). Also make the two EFI functions in question here static - they're not being referenced elsewhere. History: This commit was originally merged as bacef661 ("x86-64/efi: Use EFI to deal with platform wall clock") but it resulted in some ASUS machines no longer booting due to a firmware bug, and so was reverted in f026cfa8. A pre-emptive fix for the buggy ASUS firmware was merged in 03a1c254975e ("x86, efi: 1:1 pagetable mapping for virtual EFI calls") so now this patch can be reapplied. Signed-off-by: Jan Beulich <jbeulich@suse.com> Tested-by: Matt Fleming <matt.fleming@intel.com> Acked-by: Matthew Garrett <mjg@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com> [added commit history]
-
Xiaoyan Zhang authored
For TXT boot, while Linux kernel trys to shutdown/S3/S4/reboot, it need to jump back to tboot code and do TXT teardown work. Previously kernel zapped all mem page identity mapping (va=pa) after booting, so tboot code mem address was mapped again with identity mapping. Now kernel didn't zap the identity mapping page table, so tboot related code can remove the remapping code before trapping back now. Signed-off-by: Xiaoyan Zhang <xiaoyan.zhang@intel.com> Acked-by: Gang Wei <gang.wei@intel.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
Some firmware still needs a 1:1 (virt->phys) mapping even after we've called SetVirtualAddressMap(). So install the mapping alongside our existing kernel mapping whenever we make EFI calls in virtual mode. This bug was discovered on ASUS machines where the firmware implementation of GetTime() accesses the RTC device via physical addresses, even though that's bogus per the UEFI spec since we've informed the firmware via SetVirtualAddressMap() that the boottime memory map is no longer valid. This bug seems to be present in a lot of consumer devices, so there's not a lot we can do about this spec violation apart from workaround it. Cc: JérômeCarretero <cJ-ko@zougloub.eu> Cc: Vasco Dias <rafa.vasco@gmail.com> Acked-by: Jan Beulich <jbeulich@suse.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
There are various pieces of code in arch/x86 that require a page table with an identity mapping. Make trampoline_pgd a proper kernel page table, it currently only includes the kernel text and module space mapping. One new feature of trampoline_pgd is that it now has mappings for the physical I/O device addresses, which are inserted at ioremap() time. Some broken implementations of EFI firmware require these mappings to always be around. Acked-by: Jan Beulich <jbeulich@suse.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matt Fleming authored
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Lee, Chun-Yi authored
UEFI variable filesystem need a new mount point, so this patch add efivars kobject to efi_kobj for create a /sys/firmware/efi/efivars folder. Cc: Matthew Garrett <mjg@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Lee, Chun-Yi <jlee@suse.com> Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Jeremy Kerr authored
A write to an efivarfs file will not always result in a variable of 'count' size after the EFI SetVariable() call. We may have appended to the existing data (ie, with the EFI_VARIABLE_APPEND_WRITE attribute), or even have deleted the variable (with an authenticated variable update, with a zero datasize). This change re-reads the updated variable from firmware, to check for size changes and deletions. In the latter case, we need to drop the dentry. Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
Matthew Garrett authored
The existing EFI variables code only supports variables of up to 1024 bytes. This limitation existed in version 0.99 of the EFI specification, but was removed before any full releases. Since variables can now be larger than a single page, sysfs isn't the best interface for this. So, instead, let's add a filesystem. Variables can be read, written and created, with the first 4 bytes of each variable representing its UEFI attributes. The create() method doesn't actually commit to flash since zero-length variables can't exist per-spec. Updates from Jeremy Kerr <jeremy.kerr@canonical.com>. Signed-off-by: Matthew Garrett <mjg@redhat.com> Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
-
- 14 Oct, 2012 6 commits
-
-
Linus Torvalds authored
-
git://git.linux-mips.org/pub/scm/ralf/upstream-linusLinus Torvalds authored
Pull MIPS update from Ralf Baechle: "Cleanups and fixes for breakage that occured earlier during this merge phase. Also a few patches that didn't make the first pull request. Of those is the Alchemy work that merges code for many of the SOCs and evaluation boards thus among other code shrinkage, reduces the number of MIPS defconfigs by 5." * 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (22 commits) MIPS: SNI: Switch RM400 serial to SCCNXP driver MIPS: Remove unused empty_bad_pmd_table[] declaration. MIPS: MT: Remove kspd. MIPS: Malta: Fix section mismatch. MIPS: asm-offset.c: Delete unused irq_cpustat_t struct offsets. MIPS: Alchemy: Merge PB1100/1500 support into DB1000 code. MIPS: Alchemy: merge PB1550 support into DB1550 code MIPS: Alchemy: Single kernel for DB1200/1300/1550 MIPS: Optimize TLB refill for RI/XI configurations. MIPS: proc: Cleanup printing of ASEs. MIPS: Hardwire detection of DSP ASE Rev 2 for systems, as required. MIPS: Add detection of DSP ASE Revision 2. MIPS: Optimize pgd_init and pmd_init MIPS: perf: Add perf functionality for BMIPS5000 MIPS: perf: Split the Kconfig option CONFIG_MIPS_MT_SMP MIPS: perf: Remove unnecessary #ifdef MIPS: perf: Add cpu feature bit for PCI (performance counter interrupt) MIPS: perf: Change the "mips_perf_event" table unsupported indicator. MIPS: Align swapper_pg_dir to 64K for better TLB Refill code. vmlinux.lds.h: Allow architectures to add sections to the front of .bss ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linuxLinus Torvalds authored
Pull module signing support from Rusty Russell: "module signing is the highlight, but it's an all-over David Howells frenzy..." Hmm "Magrathea: Glacier signing key". Somebody has been reading too much HHGTTG. * 'modules-next' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (37 commits) X.509: Fix indefinite length element skip error handling X.509: Convert some printk calls to pr_devel asymmetric keys: fix printk format warning MODSIGN: Fix 32-bit overflow in X.509 certificate validity date checking MODSIGN: Make mrproper should remove generated files. MODSIGN: Use utf8 strings in signer's name in autogenerated X.509 certs MODSIGN: Use the same digest for the autogen key sig as for the module sig MODSIGN: Sign modules during the build process MODSIGN: Provide a script for generating a key ID from an X.509 cert MODSIGN: Implement module signature checking MODSIGN: Provide module signing public keys to the kernel MODSIGN: Automatically generate module signing keys if missing MODSIGN: Provide Kconfig options MODSIGN: Provide gitignore and make clean rules for extra files MODSIGN: Add FIPS policy module: signature checking hook X.509: Add a crypto key parser for binary (DER) X.509 certificates MPILIB: Provide a function to read raw data into an MPI X.509: Add an ASN.1 decoder X.509: Add simple ASN.1 grammar compiler ...
-
Matt Fleming authored
The hostprogs need access to the CONFIG_* symbols found in include/generated/autoconf.h. But commit abbf1590 ("UAPI: Partition the header include path sets and add uapi/ header directories") replaced $(LINUXINCLUDE) with $(USERINCLUDE) which doesn't contain the necessary include paths. This has the undesirable effect of breaking the EFI boot stub because the #ifdef CONFIG_EFI_STUB code in arch/x86/boot/tools/build.c is never compiled. It should also be noted that because $(USERINCLUDE) isn't exported by the top-level Makefile it's actually empty in arch/x86/boot/Makefile. Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-
Ingo Molnar authored
The UAPI commits forgot to test tooling builds such as tools/perf/, and this fixes the fallout. Manual conversion. Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-
git://git.linaro.org/people/rmk/linux-armLinus Torvalds authored
Pull ARM update from Russell King: "This is the final round of stuff for ARM, left until the end of the merge window to reduce the number of conflicts. This set contains the ARM part of David Howells UAPI changes, and a fix to the ordering of 'select' statements in ARM Kconfig files (see the appropriate commit for why this happened - thanks to Andrew Morton for pointing out the problem.) I've left this as long as I dare for this window to avoid conflicts, and I regenerated the config patch yesterday, posting it to our mailing list for review and testing. I have several acks which include successful test reports for it. However, today I notice we've got new conflicts with previously unseen code... though that conflict should be trivial (it's my changes vs a one liner.)" * 'late-for-linus' of git://git.linaro.org/people/rmk/linux-arm: ARM: config: make sure that platforms are ordered by option string ARM: config: sort select statements alphanumerically UAPI: (Scripted) Disintegrate arch/arm/include/asm Fix up fairly conflict in arch/arm/Kconfig (the select re-organization vs recent addition of GENERIC_KERNEL_EXECVE)
-
- 13 Oct, 2012 11 commits
-
-
git://git.infradead.org/users/dhowells/linux-headersLinus Torvalds authored
Pull UAPI disintegration for include/linux/{,byteorder/}*.h from David Howells: "The patches contained herein do the following: (1) Remove kernel-only stuff in linux/ppp-comp.h from the UAPI. I checked this with Paul Mackerras before I created the patch and he suggested some extra bits to unexport. (2) Remove linux/blk_types.h entirely from the UAPI as none of it is userspace applicable, and remove from the UAPI that part of linux/fs.h that was the reason for linux/blk_types.h being exported in the first place. I discussed this with Jens Axboe before creating the patch. (3) The big patch of the series to disintegrate include/linux/*.h as a unit. This could be split up, though there would be collisions in moving stuff between the two Kbuild files when the parts are merged as that file is sorted alphabetically rather than being grouped by subsystem. Of this set of headers, 17 files have changed in the UAPI exported region since the 4th and only 8 since the 9th so there isn't much change in this area - as one might expect. It should be pretty obvious and straightforward if it does come to fixing up: stuff in __KERNEL__ guards stays where it is and stuff outside moves to the same file in the include/uapi/linux/ directory. If a new file appears then things get a bit more complicated as the "headers +=" line has to move to include/uapi/linux/Kbuild. Only one new file has appeared since the 9th and I judge this type of event relatively unlikely. (4) A patch to disintegrate include/linux/byteorder/*.h as a unit. Signed-off-by: David Howells <dhowells@redhat.com>" * tag 'disintegrate-main-20121013' of git://git.infradead.org/users/dhowells/linux-headers: UAPI: (Scripted) Disintegrate include/linux/byteorder UAPI: (Scripted) Disintegrate include/linux UAPI: Unexport linux/blk_types.h UAPI: Unexport part of linux/ppp-comp.h
-
git://git.infradead.org/users/dhowells/linux-headersLinus Torvalds authored
Pull spi UAPI disintegration from David Howells: "This is to complete part of the Userspace API (UAPI) disintegration for which the preparatory patches were pulled recently. After these patches, userspace headers will be segregated into: include/uapi/linux/.../foo.h for the userspace interface stuff, and: include/linux/.../foo.h for the strictly kernel internal stuff. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Grant Likely <grant.likely@secretlab.ca>" * tag 'disintegrate-spi-20121009' of git://git.infradead.org/users/dhowells/linux-headers: UAPI: (Scripted) Disintegrate include/linux/spi
-
git://openrisc.net/jonas/linuxLinus Torvalds authored
Pull OpenRISC uapi disintegration from Jonas Bonn: "OpenRISC UAPI disintegration work from David Howells" * tag 'openrisc-uapi' of git://openrisc.net/jonas/linux: UAPI: (Scripted) Disintegrate arch/openrisc/include/asm
-
git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespaceLinus Torvalds authored
Pull user namespace compile fixes from Eric W Biederman: "This tree contains three trivial fixes. One compiler warning, one thinko fix, and one build fix" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: btrfs: Fix compilation with user namespace support enabled userns: Fix posix_acl_file_xattr_userns gid conversion userns: Properly print bluetooth socket uids
-
git://neil.brown.name/mdLinus Torvalds authored
Pull md updates from NeilBrown: - "discard" support, some dm-raid improvements and other assorted bits and pieces. * tag 'md-3.7' of git://neil.brown.name/md: (29 commits) md: refine reporting of resync/reshape delays. md/raid5: be careful not to resize_stripes too big. md: make sure manual changes to recovery checkpoint are saved. md/raid10: use correct limit variable md: writing to sync_action should clear the read-auto state. Subject: [PATCH] md:change resync_mismatches to atomic64_t to avoid races md/raid5: make sure to_read and to_write never go negative. md: When RAID5 is dirty, force reconstruct-write instead of read-modify-write. md/raid5: protect debug message against NULL derefernce. md/raid5: add some missing locking in handle_failed_stripe. MD: raid5 avoid unnecessary zero page for trim MD: raid5 trim support md/bitmap:Don't use IS_ERR to judge alloc_page(). md/raid1: Don't release reference to device while handling read error. raid: replace list_for_each_continue_rcu with new interface add further __init annotations to crypto/xor.c DM RAID: Fix for "sync" directive ineffectiveness DM RAID: Fix comparison of index and quantity for "rebuild" parameter DM RAID: Add rebuild capability for RAID10 DM RAID: Move 'rebuild' checking code to its own function ...
-
Russell King authored
-
Russell King authored
The large platform selection choice should be sorted by option string so it's easy to find the platform you're looking for. Fix the few options which are out of this order. Acked-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-
Russell King authored
As suggested by Andrew Morton: This is a pet peeve of mine. Any time there's a long list of items (header file inclusions, kconfig entries, array initalisers, etc) and someone wants to add a new item, they *always* go and stick it at the end of the list. Guys, don't do this. Either put the new item into a randomly-chosen position or, probably better, alphanumerically sort the list. lets sort all our select statements alphanumerically. This commit was created by the following perl: while (<>) { while (/\\\s*$/) { $_ .= <>; } undef %selects if /^\s*config\s+/; if (/^\s+select\s+(\w+).*/) { if (defined($selects{$1})) { if ($selects{$1} eq $_) { print STDERR "Warning: removing duplicated $1 entry\n"; } else { print STDERR "Error: $1 differently selected\n". "\tOld: $selects{$1}\n". "\tNew: $_\n"; exit 1; } } $selects{$1} = $_; next; } if (%selects and (/^\s*$/ or /^\s+help/ or /^\s+---help---/ or /^endif/ or /^endchoice/)) { foreach $k (sort (keys %selects)) { print "$selects{$k}"; } undef %selects; } print; } if (%selects) { foreach $k (sort (keys %selects)) { print "$selects{$k}"; } } It found two duplicates: Warning: removing duplicated S5P_SETUP_MIPIPHY entry Warning: removing duplicated HARDIRQS_SW_RESEND entry and they are identical duplicates, hence the shrinkage in the diffstat of two lines. We have four testers reporting success of this change (Tony, Stephen, Linus and Sekhar.) Acked-by: Jason Cooper <jason@lakedaemon.net> Acked-by: Tony Lindgren <tony@atomide.com> Acked-by: Stephen Warren <swarren@nvidia.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Sekhar Nori <nsekhar@ti.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-
David Howells authored
Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
-
David Howells authored
Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Dave Jones <davej@redhat.com>
-
David Howells authored
It seems that was linux/blk_types.h incorrectly exported to fix up some missing bits required by the exported parts of linux/fs.h (READ, WRITE, READA, etc.). So unexport linux/blk_types.h and unexport the relevant bits of linux/fs.h. Signed-off-by: David Howells <dhowells@redhat.com> cc: Jens Axboe <jaxboe@fusionio.com> cc: Tejun Heo <tj@kernel.org> cc: Al Viro <viro@ZenIV.linux.org.uk>
-