| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Apply the same rules as the anon pipe pages, only allow stealing
if no one else is using the page.
Signed-off-by: Jens Axboe <axboe@suse.de>
|
|
Currently we rely on the PIPE_BUF_FLAG_LRU flag being set correctly
to know whether we need to fiddle with page LRU state after stealing it,
however for some origins we just don't know if the page is on the LRU
list or not.
So remove PIPE_BUF_FLAG_LRU and do this check/add manually in pipe_to_file()
instead.
Signed-off-by: Jens Axboe <axboe@suse.de>
|
|
* 'audit.b10' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current:
[PATCH] Audit Filter Performance
[PATCH] Rework of IPC auditing
[PATCH] More user space subject labels
[PATCH] Reworked patch for labels on user space messages
[PATCH] change lspp ipc auditing
[PATCH] audit inode patch
[PATCH] support for context based audit filtering, part 2
[PATCH] support for context based audit filtering
[PATCH] no need to wank with task_lock() and pinning task down in audit_syscall_exit()
[PATCH] drop task argument of audit_syscall_{entry,exit}
[PATCH] drop gfp_mask in audit_log_exit()
[PATCH] move call of audit_free() into do_exit()
[PATCH] sockaddr patch
[PATCH] deal with deadlocks in audit_free()
|
|
When iptables userspace adds an ipt_standard_target, it calculates the size
of the entire entry as:
sizeof(struct ipt_entry) + XT_ALIGN(sizeof(struct ipt_standard_target))
ipt_standard_target looks like this:
struct xt_standard_target
{
struct xt_entry_target target;
int verdict;
};
xt_entry_target contains a pointer, so when compiled for 64 bit the
structure gets an extra 4 byte of padding at the end. On 32 bit
architectures where iptables aligns to 8 byte it will also have 4
byte padding at the end because it is only 36 bytes large.
The compat_ipt_standard_fn in the kernel adjusts the offsets by
sizeof(struct ipt_standard_target) - sizeof(struct compat_ipt_standard_target),
which will always result in 4, even if the structure from userspace
was already padded to a multiple of 8. On x86 this works out by
accident because userspace only aligns to 4, on all other
architectures this is broken and causes incorrect adjustments to
the size and following offsets.
Thanks to Linus for lots of debugging help and testing.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
* 'splice' of git://brick.kernel.dk/data/git/linux-2.6-block:
[PATCH] vmsplice: allow user to pass in gift pages
[PATCH] pipe: enable atomic copying of pipe data to/from user space
[PATCH] splice: call handle_ra_miss() on failure to lookup page
[PATCH] Add ->splice_read/splice_write to def_blk_fops
[PATCH] pipe: introduce ->pin() buffer operation
[PATCH] splice: fix bugs in pipe_to_file()
[PATCH] splice: fix bugs with stealing regular pipe pages
|
|
Add an nid member to the spu structure, and store the numa id of the spu there
on creation.
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Change of_node_to_nid() to traverse the device tree, looking for a numa id.
Cell uses this to assign ids to SPUs, which are children of the CPU node.
Existing users of of_node_to_nid() are altered to use of_node_to_nid_single(),
which doesn't do the traversal.
Export an attach_sysdev_to_node() function, allowing system devices (eg.
SPUs) to link themselves into the numa topology in sysfs.
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
If SPLICE_F_GIFT is set, the user is basically giving this pages away to
the kernel. That means we can steal them for eg page cache uses instead
of copying it.
The data must be properly page aligned and also a multiple of the page size
in length.
Signed-off-by: Jens Axboe <axboe@suse.de>
|
|
The pipe ->map() method uses kmap() to virtually map the pages, which
is both slow and has known scalability issues on SMP. This patch enables
atomic copying of pipe pages, by pre-faulting data and using kmap_atomic()
instead.
lmbench bw_pipe and lat_pipe measurements agree this is a Good Thing. Here
are results from that on a UP machine with highmem (1.5GiB of RAM), running
first a UP kernel, SMP kernel, and SMP kernel patched.
Vanilla-UP:
Pipe bandwidth: 1622.28 MB/sec
Pipe bandwidth: 1610.59 MB/sec
Pipe bandwidth: 1608.30 MB/sec
Pipe latency: 7.3275 microseconds
Pipe latency: 7.2995 microseconds
Pipe latency: 7.3097 microseconds
Vanilla-SMP:
Pipe bandwidth: 1382.19 MB/sec
Pipe bandwidth: 1317.27 MB/sec
Pipe bandwidth: 1355.61 MB/sec
Pipe latency: 9.6402 microseconds
Pipe latency: 9.6696 microseconds
Pipe latency: 9.6153 microseconds
Patched-SMP:
Pipe bandwidth: 1578.70 MB/sec
Pipe bandwidth: 1579.95 MB/sec
Pipe bandwidth: 1578.63 MB/sec
Pipe latency: 9.1654 microseconds
Pipe latency: 9.2266 microseconds
Pipe latency: 9.1527 microseconds
Signed-off-by: Jens Axboe <axboe@suse.de>
|
|
The ->map() function is really expensive on highmem machines right now,
since it has to use the slower kmap() instead of kmap_atomic(). Splice
rarely needs to access the virtual address of a page, so it's a waste
of time doing it.
Introduce ->pin() to take over the responsibility of making sure the
page data is valid. ->map() is then reduced to just kmap(). That way we
can also share a most of the pipe buffer ops between pipe.c and splice.c
Signed-off-by: Jens Axboe <axboe@suse.de>
|
|
Found by Oleg Nesterov <oleg@tv-sign.ru>, fixed by me.
- Only allow full pages to go to the page cache.
- Check page != buf->page instead of using PIPE_BUF_FLAG_STOLEN.
- Remember to clear 'stolen' if add_to_page_cache() fails.
And as a cleanup on that:
- Make the bottom fall-through logic a little less convoluted. Also make
the steal path hold an extra reference to the page, so we don't have
to differentiate between stolen and non-stolen at the end.
Signed-off-by: Jens Axboe <axboe@suse.de>
|
|
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
[TG3]: Update version and reldate
[TG3]: Fix bug in nvram write
[TG3]: Add reset_phy parameter to chip reset functions
[TG3]: Reset chip when changing MAC address
[TG3]: Add phy workaround
[TG3]: Call netif_carrier_off() during phy reset
[IPV6]: Fix race in route selection.
[XFRM]: fix incorrect xfrm_policy_afinfo_lock use
[XFRM]: fix incorrect xfrm_state_afinfo_lock use
[TCP]: Fix unlikely usage in tcp_transmit_skb()
[XFRM]: fix softirq-unsafe xfrm typemap->lock use
[IPSEC]: Fix IP ID selection
[NET]: use hlist_unhashed()
[IPV4]: inet_init() -> fs_initcall
[NETLINK]: cleanup unused macro in net/netlink/af_netlink.c
[PKT_SCHED] netem: fix loss
[X25]: fix for spinlock recurse and spinlock lockup with timer handler
|
|
* master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6:
[SPARC64]: Disable preemption during flush_tlb_pending().
[SPARC64]: Kill __flush_tlb_page() prototype.
|
|
* git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: make EVIOCGSND return meaningful data
Input: ressurect EVIOCGREP and EVIOCSREP
Input: psmouse - fix new device detection logic
Input: move input_device_id to mod_devicetable.h
Input: allow using several chords for braille
Input: allow passing NULL to input_free_device()
Input: spitzkbd - fix the reversed Address and Calender keys
Input: ads7846 - improve filtering for thumb press accuracy
Input: ads7846 - report 0 pressure value along with pen up event
Input: ads7846 - handle IRQs that were latched during disabled IRQs
Input: ads7846 - miscellaneous fixes
Input: ads7846 - use msleep() instead of udelay() in suspend
Input: ads7846 - debouncing and rudimentary sample filtering
Input: ads7846 - power down ADC a bit later
Input: ads7846 - add pen_down sysfs attribute
Input: wistron - add support for Fujitsu N3510
Input: wistron - add signature for Amilo M7400
|
|
* git://git.kernel.org/pub/scm/linux/kernel/git/perex/alsa: (22 commits)
[ALSA] via82xx - Use DXS_SRC as default for VIA8235/8237/8251 chips
[ALSA] hda-codec - Add model entry for ASUS Z62F
[ALSA] PCMCIA sound devices shouldn't depend on ISA
[ALSA] hda-codec - Fix capture from line-in on VAIO SZ/FE laptops
[ALSA] Fix Oops at rmmod with CONFIG_SND_VERBOSE_PROCFS=n
[ALSA] PCM core - introduce CONFIG_SND_PCM_XRUN_DEBUG
[ALSA] adding __devinitdata to pci_device_id
[ALSA] add __devinitdata to all pci_device_id
[ALSA] hda-codec - Add codec id for AD1988B codec chip
[ALSA] hda-codec - Add model entry for ASUS M9 laptop
[ALSA] pcxhr - Fix a compiler warning on 64bit architectures
[ALSA] via82xx: tweak VT8251 workaround
[ALSA] intel8x0 - Disable ALI5455 SPDIF-input
[ALSA] via82xx: add support for VIA VT8251 (AC'97)
[ALSA] Fix typos and add information about Jack support to Audiophile-Usb.txt
[ALSA] Fix double free in error path of miro driver
[ALSA] hda-codec - Add entry for Epox EP-5LDA+ GLi
[ALSA] sound/pci/: remove duplicate #include's
[ALSA] hda-codec - Use model 'hp' for all HP laptops with AD1981HD
[ALSA] continue on IS_ERR from platform device registration
...
|
|
1) The audit_ipc_perms() function has been split into two different
functions:
- audit_ipc_obj()
- audit_ipc_set_perm()
There's a key shift here... The audit_ipc_obj() collects the uid, gid,
mode, and SElinux context label of the current ipc object. This
audit_ipc_obj() hook is now found in several places. Most notably, it
is hooked in ipcperms(), which is called in various places around the
ipc code permforming a MAC check. Additionally there are several places
where *checkid() is used to validate that an operation is being
performed on a valid object while not necessarily having a nearby
ipcperms() call. In these locations, audit_ipc_obj() is called to
ensure that the information is captured by the audit system.
The audit_set_new_perm() function is called any time the permissions on
the ipc object changes. In this case, the NEW permissions are recorded
(and note that an audit_ipc_obj() call exists just a few lines before
each instance).
2) Support for an AUDIT_IPC_SET_PERM audit message type. This allows
for separate auxiliary audit records for normal operations on an IPC
object and permissions changes. Note that the same struct
audit_aux_data_ipcctl is used and populated, however there are separate
audit_log_format statements based on the type of the message. Finally,
the AUDIT_IPC block of code in audit_free_aux() was extended to handle
aux messages of this new type. No more mem leaks I hope ;-)
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
Hi,
The patch below builds upon the patch sent earlier and adds subject label to
all audit events generated via the netlink interface. It also cleans up a few
other minor things.
Signed-off-by: Steve Grubb <sgrubb@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
The below patch should be applied after the inode and ipc sid patches.
This patch is a reworking of Tim's patch that has been updated to match
the inode and ipc patches since its similar.
[updated:
> Stephen Smalley also wanted to change a variable from isec to tsec in the
> user sid patch. ]
Signed-off-by: Steve Grubb <sgrubb@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
Hi,
The patch below converts IPC auditing to collect sid's and convert to context
string only if it needs to output an audit record. This patch depends on the
inode audit change patch already being applied.
Signed-off-by: Steve Grubb <sgrubb@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
Previously, we were gathering the context instead of the sid. Now in this patch,
we gather just the sid and convert to context only if an audit event is being
output.
This patch brings the performance hit from 146% down to 23%
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
The following patch provides selinux interfaces that will allow the audit
system to perform filtering based on the process context (user, role, type,
sensitivity, and clearance). These interfaces will allow the selinux
module to perform efficient matches based on lower level selinux constructs,
rather than relying on context retrievals and string comparisons within
the audit module. It also allows for dominance checks on the mls portion
of the contexts that are impossible with only string comparisons.
Signed-off-by: Darrel Goeddel <dgoeddel@trustedcs.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
... it's always current, and that's a good thing - allows simpler locking.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
This function no longer exists.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Use hlist_unhashed() rather than accessing inside data structure.
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc:
[PATCH] powerpc: update cell_defconfig
[PATCH] spufs: Disable local interrupts for SPE hash_page calls.
[PATCH] powerpc: Add cputable entry for POWER6
[PATCH] ppc32 CPM_UART: Fixed odd address translations
[PATCH] ppc32: Update board-specific code of the CPM UART users
[PATCH] ppc32 CPM_UART: Convert to use platform devices
[PATCH] ppc32: odd fixes and improvements in ppc_sys
[PATCH] powerpc: Wire up *at syscalls
[PATCH] ppc32: add 440GX erratum 440_43 workaround
[PATCH] powerpc: Use check_legacy_ioport() on ppc32 too.
[PATCH] powerpc64: Fix loading of modules without a .toc section
[PATCH] sound/ppc: snd_pmac_toonie_init should be __init
powerpc/pseries: Tell firmware our capabilities on new machines
[PATCH] powerpc: Fix pagetable bloat for hugepages
|
|
The FXSAVE information leak patch introduced a bug in FP exception
handling: it clears FP exceptions only when there are already
none outstanding. Mikael Pettersson reported that causes problems
with the Erlang runtime and has tested this fix.
Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com>
Acked-by: Mikael Pettersson <mikpe@it.uu.se>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
While writing to an event device allows to set repeat rate for an
individual input device there is no way to retrieve current settings
so we need to ressurect EVIOCGREP. Also ressurect EVIOCSREP so we
have a symmetrical interface.
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
|
|
|
|
Add a cputable entry for the POWER6 processor.
The SIHV and SIPR bits in the mmcra have moved in POWER6, so disable
support for that until oprofile is fixed.
Also tell firmware that we know about POWER6.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
|
|
Add a read_mostly section and define __read_mostly to prevent cache line
pollution due to writes for mostly read variables. In addition fix the
incorrect alignment of the cache_line_aligned data section. s390 has a
cacheline size of 256 bytes.
Signed-off-by: Christian Borntraeger <cborntra@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Add support for atomic futex operations.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
- Add new SA_PROBEIRQ which suppresses the new sharing-mismatch warning.
Some drivers like to use request_irq() to find an unused interrupt slot.
- Use it in i82365.c
- Kill unused SA_PROBE.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This consists of offsets fix in ..._devices.c, and update of
ppc_sys_fixup_mem_resource() function to prevent subsequent fixups
Signed-off-by: Vitaly Bordug <vbordug@ru.mvista.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
|
|
Wire up *at syscalls.
This patch has been tested on ppc64 (using glibc's testsuite, both 32bit
and 64bit), and compile-tested for ppc32 (I have currently no ppc32 system
available, but I expect no problems).
Signed-off-by: Andreas Schwab <schwab@suse.de>
Signed-off-by: Paul Mackerras <paulus@samba.org>
|
|
This patch adds workaround for PPC 440GX erratum 440_43. According to
this erratum spurious MachineChecks (caused by L1 cache parity) can
happen during DataTLB miss processing. We disable L1 cache parity
checking for 440GX rev.C and rev.F
Signed-off-by: Eugene Surovegin <ebs@ebshome.net>
Signed-off-by: Paul Mackerras <paulus@samba.org>
|
|
Some people report that we die on some Macs when we are expecting to
catch machine checks after poking at some random I/O address. I'd seen
it happen on my dual G4 with serial ports until we fixed those to use
OF, but now other users are reporting it with i8042.
This expands the use of check_legacy_ioport() to avoid that situation
even on 32-bit kernels.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
|
|
At present, ARCH=powerpc kernels can waste considerable space in
pagetables when making large hugepage mappings. Hugepage PTEs go in
PMD pages, but each PMD page maps 256M and so contains only 16
hugepage PTEs (128 bytes of data), but takes up a 1024 byte
allocation. With CONFIG_PPC_64K_PAGES enabled (64k base page size),
the situation is worse. Now hugepage PTEs are at the PTE page level
(also mapping 256M), so we store 16 hugepage PTEs in a 64k allocation.
The PowerPC MMU already means that any 256M region is either all
hugepage, or all normal pages. Thus, with some care, we can use a
different allocation for the hugepage PTE tables and only allocate the
128 bytes necessary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
|
|
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
[IA64] update sn2 defconfig
[IA64] Add mca recovery failure messages
[IA64-SGI] fix SGI Altix tioce_reserve_m32() bug
[IA64] enable dumps to capture second page of kernel stack
[IA64-SGI] - Reduce overhead of reading sn_topology
[IA64-SGI] - Fix discover of nearest cpu node to IO node
[IA64] IOC4 config option ordering
[IA64] Setup an IA64 specific reclaim distance
[IA64] eliminate compile time warnings
[IA64] eliminate compile time warnings
[IA64-SGI] SN SAL call to inject memory errors
[IA64] - Fix MAX_PXM_DOMAINS for systems with > 256 nodes
[IA64] Remove unused variable in sn_sal.h
[IA64] Remove redundant NULL checks before kfree
[IA64] wire up compat_sys_adjtimex()
|
|
In SLES10 (2.6.16) crash dumping (in my experience, LKCD) is unable to
capture the second page of the 2-page task/stack allocation.
This is particularly troublesome for dump analysis, as the stack traceback
cannot be done.
(A similar convention is probably needed throughout the kernel to make
kernel multi-page allocations detectable for dumping)
Multi-page kernel allocations are represented by the single page structure
associated with the first page of the allocation. The page structures
associated with the other pages are unintialized.
If the dumper is selecting only kernel pages it has no way to identify
any but the first page of the allocation.
The fix is to make the task/stack allocation a compound page.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
|
|
Fix a bug that causes discovery of the nearest node/cpu to
a TIO (IO node) to fail.
Signed-off-by: Jack Steiner <steiner@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
|
|
* master.kernel.org:/pub/scm/linux/kernel/git/gregkh/driver-2.6:
[PATCH] Added URI of "linux kernel development process"
[PATCH] Kobject: possible cleanups
[PATCH] Fix OCFS2 warning when DEBUG_FS is not enabled
[PATCH] Kobject: fix build error
[PATCH] Frame buffer: remove cmap sysfs interface
|
|
* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus:
[MIPS] Fix branch emulation for floating-point exceptions.
[MIPS] Cleanup inode->r_dev usage.
[MIPS] Update MIPS defconfigs.
[MIPS] Get rid of CONFIG_ADVANCED.
[MIPS] Kconfig: Clarify description of CROSSCOMPILE.
[MIPS] 24K LV: Add core card id.
[MIPS] Sparse: fix sparse for 64-bit kernels.
[MIPS] Use __ffs() instead of ffs() in ip32_irq0().
[MIPS] Fix bitops for MIPS32/MIPS64 CPUs.
[MIPS] Fix ip27 build.
[MIPS] Oprofile: fix sparse warning.
[MIPS] Fix oprofile module unloading
|
|
* 'splice' of git://brick.kernel.dk/data/git/linux-2.6-block:
[PATCH] splice: make the read-side do batched page lookups
[PATCH] Add find_get_pages_contig(): contiguous variant of find_get_pages()
[PATCH] splice: switch to using page_cache_readahead()
|
|
This patch contains the following possible cleanups:
- #if 0 the following unused global function:
- subsys_remove_file()
- remove the following unused EXPORT_SYMBOL's:
- kset_find_obj
- subsystem_init
- remove the following unused EXPORT_SYMBOL_GPL:
- kobject_add_dir
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Fix the following warning which happens when OCFS2_FS is enabled but
DEBUG_FS isn't:
fs/ocfs2/dlmglue.c: In function `ocfs2_dlm_init_debug':
fs/ocfs2/dlmglue.c:2036: warning: passing arg 5 of `debugfs_create_file' discards qualifiers from pointer target type
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Joel Becker <Joel.Becker@oracle.com>
Acked-by: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This fixes a build error for various odd combinations of CONFIG_HOTPLUG
and CONFIG_NET.
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Cc: Nigel Cunningham <ncunningham@cyclades.com>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Fixed Oops at rmmod with CONFIG_SND_VERBOSE_PROCFS=n.
Add ifdef to struct fields for optimization and better compile
checks.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
|
|
Proposed fix for ptep_get_and_clear_full PAE bug. Pte_clear had the same bug,
so use the same fix for both. Turns out pmd_clear had it as well, but pgds
are not affected.
The problem is rather intricate. Page table entries in PAE mode are 64-bits
wide, but the only atomic 8-byte write operation available in 32-bit mode is
cmpxchg8b, which is expensive (at least on P4), and thus avoided. But it can
happen that the processor may prefetch entries into the TLB in the middle of an
operation which clears a page table entry. So one must always clear the P-bit
in the low word of the page table entry first when clearing it.
Since the sequence *ptep = __pte(0) leaves the order of the write dependent on
the compiler, it must be coded explicitly as a clear of the low word followed
by a clear of the high word. Further, there must be a write memory barrier
here to enforce proper ordering by the compiler (and, in the future, by the
processor as well).
On > 4GB memory machines, the implementation of pte_clear for PAE was clearly
deficient, as it could leave virtual mappings of physical memory above 4GB
aliased to memory below 4GB in the TLB. The implementation of
ptep_get_and_clear_full has a similar bug, although not nearly as likely to
occur, since the mappings being cleared are in the process of being destroyed,
and should never be dereferenced again.
But, as luck would have it, it is possible to trigger bugs even without ever
dereferencing these bogus TLB mappings, even if the clear is followed fairly
soon after with a TLB flush or invalidation. The problem is that memory above
4GB may now be aliased into the first 4GB of memory, and in fact, may hit a
region of memory with non-memory semantics. These regions include AGP and PCI
space. As such, these memory regions are not cached by the processor. This
introduces the bug.
The processor can speculate memory operations, including memory writes, as long
as they are committed with the proper ordering. Speculating a memory write to
a linear address that has a bogus TLB mapping is possible. Normally, the
speculation is harmless. But for cached memory, it does leave the falsely
speculated cacheline unmodified, but in a dirty state. This cache line will be
eventually written back. If this cacheline happens to intersect a region of
memory that is not protected by the cache coherency protocol, it can corrupt
data in I/O memory, which is generally a very bad thing to do, and can cause
total system failure or just plain undefined behavior.
These bugs are extremely unlikely, but the severity is of such magnitude, and
the fix so simple that I think fixing them immediately is justified. Also,
they are nearly impossible to debug.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
|
David S. Miller
Jens Axboe
Linus Torvalds
Patrick McHardy
Jeremy Kerr
Steve Grubb
Darrel Goeddel
Al Viro
Akinobu Mita
Chuck Ebbert
Dmitry Torokhov
Anton Blanchard
Christian Borntraeger
Martin Schwidefsky
Andrew Morton
Vitaly Bordug
Andreas Schwab
Eugene Surovegin
David Woodhouse
David Gibson
Cliff Wickman
Jack Steiner
Adrian Bunk
Jean Delvare
Kay Sievers
Takashi Iwai
Zachary Amsden
Chris Dearman