- 01 May, 2013 2 commits
-
-
Jiri Slaby authored
commit b0de59b5 upstream. On http://vladz.devzero.fr/013_ptmx-timing.php, we can see how to find out length of a password using timestamps of /dev/ptmx. It is documented in "Timing Analysis of Keystrokes and Timing Attacks on SSH". To avoid that problem, do not update time when reading from/writing to a TTY. I am afraid of regressions as this is a behavior we have since 0.97 and apps may expect the time to be current, e.g. for monitoring whether there was a change on the TTY. Now, there is no change. So this would better have a lot of testing before it goes upstream. References: CVE-2013-0160 Signed-off-by:
Jiri Slaby <jslaby@suse.cz> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Zhao Hongjiang authored
commit 91d80a84 upstream. dprintk() shouldn't access @ring after it's unmapped. Signed-off-by:
Zhao Hongjiang <zhaohongjiang@huawei.com> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
-
- 26 Apr, 2013 27 commits
-
-
Greg Kroah-Hartman authored
-
Josef Bacik authored
commit 4bc4bee4 upstream. While trying to track down a tree log replay bug I noticed that fsck was always complaining about nbytes not being right for our fsynced file. That is because the new fsync stuff doesn't wait for ordered extents to complete, so the inodes nbytes are not necessarily updated properly when we log it. So to fix this we need to set nbytes to whatever it is on the inode that is on disk, so when we replay the extents we can just add the bytes that are being added as we replay the extent. This makes it work for the case that we have the wrong nbytes or the case that we logged everything and nbytes is actually correct. With this I'm no longer getting nbytes errors out of btrfsck. Signed-off-by:
Josef Bacik <jbacik@fusionio.com> Signed-off-by:
Chris Mason <chris.mason@fusionio.com> Signed-off-by:
Lingzhu Xiang <lxiang@redhat.com> Reviewed-by:
CAI Qian <caiqian@redhat.com> Signed-off-by:
-
Linus Torvalds authored
commit 8558e4a2 upstream. This is my example conversion of a few existing mmap users. The mtdchar case is actually disabled right now (and stays disabled), but I did it because it showed up on my "git grep", and I was familiar with the code due to fixing an overflow problem in the code in commit 9c603e53 ("mtdchar: fix offset overflow detection"). Signed-off-by:
-
Linus Torvalds authored
commit 2323036d upstream. This is my example conversion of a few existing mmap users. The HPET case is simple, widely available, and easy to test (Clemens Ladisch sent a trivial test-program for it). Test-program-by:
Clemens Ladisch <clemens@ladisch.de> Signed-off-by:
-
Linus Torvalds authored
commit fc9bbca8 upstream. This is my example conversion of a few existing mmap users. The fb_mmap() case is a good example because it is a bit more complicated than some: fb_mmap() mmaps one of two different memory areas depending on the page offset of the mmap (but happily there is never any mixing of the two, so the helper function still works). Signed-off-by:
-
Linus Torvalds authored
commit 0fe09a45 upstream. This is my example conversion of a few existing mmap users. The pcm mmap case is one of the more straightforward ones. Acked-by:
Takashi Iwai <tiwai@suse.de> Signed-off-by:
-
Linus Torvalds authored
commit b4cbb197 upstream. Various drivers end up replicating the code to mmap() their memory buffers into user space, and our core memory remapping function may be very flexible but it is unnecessarily complicated for the common cases to use. Our internal VM uses pfn's ("page frame numbers") which simplifies things for the VM, and allows us to pass physical addresses around in a denser and more efficient format than passing a "phys_addr_t" around, and having to shift it up and down by the page size. But it just means that drivers end up doing that shifting instead at the interface level. It also means that drivers end up mucking around with internal VM things like the vma details (vm_pgoff, vm_start/end) way more than they really need to. So this just exports a function to map a certain physical memory range into user space (using a phys_addr_t based interface that is much more natural for a driver) and hides all the complexity from the driver. Some drivers will still end up tweaking the vm_page_prot details for things like prefetching or cacheability etc, but that's actually relevant to the driver, rather than caring about what the page offset of the mapping is into the particular IO memory region. Acked-by:
-
Dave Airlie authored
commit 054430e7 upstream. Okay so Alan's patch handled the case where there was no registered fbcon, however the other path entered in set_con2fb_map pit. In there we called fbcon_takeover, but we also took the console lock in a couple of places. So push the console lock out to the callers of set_con2fb_map, this means fbmem and switcheroo needed to take the lock around the fb notifier entry points that lead to this. This should fix the efifb regression seen by Maarten. Tested-by:
Maarten Lankhorst <maarten.lankhorst@canonical.com> Tested-by:
Lu Hua <huax.lu@intel.com> Signed-off-by:
Dave Airlie <airlied@redhat.com> Signed-off-by:
-
Stephane Eranian authored
commit f1923820 upstream. The valid mask for both offcore_response_0 and offcore_response_1 was wrong for SNB/SNB-EP, IVB/IVB-EP. It was possible to write to reserved bit and cause a GP fault crashing the kernel. This patch fixes the problem by correctly marking the reserved bits in the valid mask for all the processors mentioned above. A distinction between desktop and server parts is introduced because bits 24-30 are only available on the server parts. This version of the patch is just a rebase to perf/urgent tree and should apply to older kernels as well. Signed-off-by:
Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: jolsa@redhat.com Cc: ak@linux.intel.com Signed-off-by:
Ingo Molnar <mingo@kernel.org> Signed-off-by:
-
Tommi Rantala authored
commit 8176cced upstream. Trinity discovered that we fail to check all 64 bits of attr.config passed by user space, resulting to out-of-bounds access of the perf_swevent_enabled array in sw_perf_event_destroy(). Introduced in commit b0a873eb ("perf: Register PMU implementations"). Signed-off-by:
Tommi Rantala <tt.rantala@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Link: http://lkml.kernel.org/r/1365882554-30259-1-git-send-email-tt.rantala@gmail.comSigned-off-by:
-
Mathias Krause authored
commit 72a763d8 upstream. The current code does not set the msg_namelen member to 0 and therefore makes net/socket.c leak the local sockaddr_storage variable to userland -- 128 bytes of kernel stack memory. Fix that. Signed-off-by:
Mathias Krause <minipli@googlemail.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by:
-
Rafał Miłecki authored
commit 46fc4c90 upstream. And make use of it in b43. This fixes a regression introduced with 49d55cef b43: N-PHY: implement spurious tone avoidance This commit made BCM4322 use only MCS 0 on channel 13, which of course resulted in performance drop (down to 0.7Mb/s). Reported-by:
Stefan Brüns <stefan.bruens@rwth-aachen.de> Signed-off-by:
Rafał Miłecki <zajec5@gmail.com> Signed-off-by:
John W. Linville <linville@tuxdriver.com> Signed-off-by:
-
Felix Fietkau authored
commit f09a8785 upstream. The hardware parsing of Control Wrapper Frames needs to be disabled, as it has been causing spurious decryption error reports. The initvals for other chips have been updated to disable it, but AR9580 was left out for some reason. Signed-off-by:
Felix Fietkau <nbd@openwrt.org> Signed-off-by:
-
Felix Fietkau authored
commit 319e7bd9 upstream. Since the firmware has been open sourced, the minor version has been bumped to 1.4 and the API/ABI will stay compatible across further 1.x releases. Signed-off-by:
-
Will Deacon authored
commit cb2d8b34 upstream. Events may be created with attr->disabled == 1 and attr->enable_on_exec == 1, which confuses the group validation code because events with the PERF_EVENT_STATE_OFF are not considered candidates for scheduling, which may lead to failure at group scheduling time. This patch fixes the validation check for ARM, so that events in the OFF state are still considered when enable_on_exec is true. Reported-by:
Sudeep KarkadaNagesha <Sudeep.KarkadaNagesha@arm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Jiri Olsa <jolsa@redhat.com> Signed-off-by:
Will Deacon <will.deacon@arm.com> Signed-off-by:
Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by:
-
Illia Ragozin authored
commit cd272d1e upstream. On Feroceon the L2 cache becomes non-coherent with the CPU when the L1 caches are disabled. Thus the L2 needs to be invalidated after both L1 caches are disabled. On kexec before the starting the code for relocation the kernel, the L1 caches are disabled in cpu_froc_fin (cpu_v7_proc_fin for Feroceon), but after L2 cache is never invalidated, because inv_all is not set in cache-feroceon-l2.c. So kernel relocation and decompression may has (and usually has) errors. Setting the function enables L2 invalidation and fixes the issue. Signed-off-by:
Illia Ragozin <illia.ragozin@grapecom.com> Acked-by:
Jason Cooper <jason@lakedaemon.net> Signed-off-by:
-
Tejun Heo authored
commit 383efcd0 upstream. try_to_wake_up_local() should only be invoked to wake up another task in the same runqueue and BUG_ON()s are used to enforce the rule. Missing try_to_wake_up_local() can stall workqueue execution but such stalls are likely to be finite either by another work item being queued or the one blocked getting unblocked. There's no reason to trigger BUG while holding rq lock crashing the whole system. Convert BUG_ON()s in try_to_wake_up_local() to WARN_ON_ONCE()s. Signed-off-by:
Tejun Heo <tj@kernel.org> Acked-by:
Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20130318192234.GD3042@htj.dyndns.orgSigned-off-by:
-
Andrew Honig authored
commit 8f964525 upstream. This patch adds support for kvm_gfn_to_hva_cache_init functions for reads and writes that will cross a page. If the range falls within the same memslot, then this will be a fast operation. If the range is split between two memslots, then the slower kvm_read_guest and kvm_write_guest are used. Tested: Test against kvm_clock unit tests. Signed-off-by:
Andrew Honig <ahonig@google.com> Signed-off-by:
Gleb Natapov <gleb@redhat.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by:
-
Andy Honig authored
commit a2c118bf upstream. If the guest specifies a IOAPIC_REG_SELECT with an invalid value and follows that with a read of the IOAPIC_REG_WINDOW KVM does not properly validate that request. ioapic_read_indirect contains an ASSERT(redir_index < IOAPIC_NUM_PINS), but the ASSERT has no effect in non-debug builds. In recent kernels this allows a guest to cause a kernel oops by reading invalid memory. In older kernels (pre-3.3) this allows a guest to read from large ranges of host memory. Tested: tested against apic unit tests. Signed-off-by:
Marcelo Tosatti <mtosatti@redhat.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by:
-
Andy Honig authored
commit 0b79459b upstream. There is a potential use after free issue with the handling of MSR_KVM_SYSTEM_TIME. If the guest specifies a GPA in a movable or removable memory such as frame buffers then KVM might continue to write to that address even after it's removed via KVM_SET_USER_MEMORY_REGION. KVM pins the page in memory so it's unlikely to cause an issue, but if the user space component re-purposes the memory previously used for the guest, then the guest will be able to corrupt that memory. Tested: Tested against kvmclock unit test Signed-off-by:
-
Andy Honig authored
commit c300aa64 upstream. If the guest sets the GPA of the time_page so that the request to update the time straddles a page then KVM will write onto an incorrect page. The write is done byusing kmap atomic to get a pointer to the page for the time structure and then performing a memcpy to that page starting at an offset that the guest controls. Well behaved guests always provide a 32-byte aligned address, however a malicious guest could use this to corrupt host kernel memory. Tested: Tested against kvmclock unit test. Signed-off-by:
-
Vyacheslav Dubeyko authored
commit 12f267a2 upstream. Change a u32 to loff_t hfsplus_file_truncate(). Signed-off-by:
Vyacheslav Dubeyko <slava@dubeyko.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hin-Tak Leung <htl10@users.sourceforge.net> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
-
Emese Revfy authored
commit b9e146d8 upstream. This fixes a kernel memory contents leak via the tkill and tgkill syscalls for compat processes. This is visible in the siginfo_t->_sifields._rt.si_sigval.sival_ptr field when handling signals delivered from tkill. The place of the infoleak: int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { ... put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); ... } Signed-off-by:
Emese Revfy <re.emese@gmail.com> Reviewed-by:
PaX Team <pageexec@freemail.hu> Signed-off-by:
Kees Cook <keescook@chromium.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by:
-
Naoya Horiguchi authored
commit 9cc3a5bd upstream. With applying the previous patch "hugetlbfs: stop setting VM_DONTDUMP in initializing vma(VM_HUGETLB)" to reenable hugepage coredump, if a memory error happens on a hugepage and the affected processes try to access the error hugepage, we hit VM_BUG_ON(atomic_read(&page->_count) <= 0) in get_page(). The reason for this bug is that coredump-related code doesn't recognise "hugepage hwpoison entry" with which a pmd entry is replaced when a memory error occurs on a hugepage. In other words, physical address information is stored in different bit layout between hugepage hwpoison entry and pmd entry, so follow_hugetlb_page() which is called in get_dump_page() returns a wrong page from a given address. The expected behavior is like this: absent is_swap_pte FOLL_DUMP Expected behavior ------------------------------------------------------------------- true false false hugetlb_fault false true false hugetlb_fault false false false return page true false true skip page (to avoid allocation) false true true hugetlb_fault false false true return page With this patch, we can call hugetlb_fault() and take proper actions (we wait for migration entries, fail with VM_FAULT_HWPOISON_LARGE for hwpoisoned entries,) and as the result we can dump all hugepages except for hwpoisoned ones. Signed-off-by:
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Rik van Riel <riel@redhat.com> Acked-by:
Michal Hocko <mhocko@suse.cz> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Acked-by:
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by:
David Rientjes <rientjes@google.com> Signed-off-by:
-
Christoph Fritz authored
commit 0443de5f upstream. To get correct endianes on little endian cpus (like arm) while reading device tree properties, this patch replaces of_get_property() with of_property_read_u32(). While there use of_property_read_bool() for the handling of the boolean "nxp,no-comparator-bypass" property. Signed-off-by:
Christoph Fritz <chf.fritz@googlemail.com> Signed-off-by:
Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by:
-
Michael Bohan authored
commit 84cc8fd2 upstream. The current code makes the assumption that a cpu_base lock won't be held if the CPU corresponding to that cpu_base is offline, which isn't always true. If a hrtimer is not queued, then it will not be migrated by migrate_hrtimers() when a CPU is offlined. Therefore, the hrtimer's cpu_base may still point to a CPU which has subsequently gone offline if the timer wasn't enqueued at the time the CPU went down. Normally this wouldn't be a problem, but a cpu_base's lock is blindly reinitialized each time a CPU is brought up. If a CPU is brought online during the period that another thread is performing a hrtimer operation on a stale hrtimer, then the lock will be reinitialized under its feet, and a SPIN_BUG() like the following will be observed: <0>[ 28.082085] BUG: spinlock already unlocked on CPU#0, swapper/0/0 <0>[ 28.087078] lock: 0xc4780b40, value 0x0 .magic: dead4ead, .owner: <none>/-1, .owner_cpu: -1 <4>[ 42.451150] [<c0014398>] (unwind_backtrace+0x0/0x120) from [<c0269220>] (do_raw_spin_unlock+0x44/0xdc) <4>[ 42.460430] [<c0269220>] (do_raw_spin_unlock+0x44/0xdc) from [<c071b5bc>] (_raw_spin_unlock+0x8/0x30) <4>[ 42.469632] [<c071b5bc>] (_raw_spin_unlock+0x8/0x30) from [<c00a9ce0>] (__hrtimer_start_range_ns+0x1e4/0x4f8) <4>[ 42.479521] [<c00a9ce0>] (__hrtimer_start_range_ns+0x1e4/0x4f8) from [<c00aa014>] (hrtimer_start+0x20/0x28) <4>[ 42.489247] [<c00aa014>] (hrtimer_start+0x20/0x28) from [<c00e6190>] (rcu_idle_enter_common+0x1ac/0x320) <4>[ 42.498709] [<c00e6190>] (rcu_idle_enter_common+0x1ac/0x320) from [<c00e6440>] (rcu_idle_enter+0xa0/0xb8) <4>[ 42.508259] [<c00e6440>] (rcu_idle_enter+0xa0/0xb8) from [<c000f268>] (cpu_idle+0x24/0xf0) <4>[ 42.516503] [<c000f268>] (cpu_idle+0x24/0xf0) from [<c06ed3c0>] (rest_init+0x88/0xa0) <4>[ 42.524319] [<c06ed3c0>] (rest_init+0x88/0xa0) from [<c0c00978>] (start_kernel+0x3d0/0x434) As an example, this particular crash occurred when hrtimer_start() was executed on CPU #0. The code locked the hrtimer's current cpu_base corresponding to CPU #1. CPU #0 then tried to switch the hrtimer's cpu_base to an optimal CPU which was online. In this case, it selected the cpu_base corresponding to CPU #3. Before it could proceed, CPU #1 came online and reinitialized the spinlock corresponding to its cpu_base. Thus now CPU #0 held a lock which was reinitialized. When CPU #0 finally ended up unlocking the old cpu_base corresponding to CPU #1 so that it could switch to CPU #3, we hit this SPIN_BUG() above while in switch_hrtimer_base(). CPU #0 CPU #1 ---- ---- ... <offline> hrtimer_start() lock_hrtimer_base(base #1) ... init_hrtimers_cpu() switch_hrtimer_base() ... ... raw_spin_lock_init(&cpu_base->lock) raw_spin_unlock(&cpu_base->lock) ... <spin_bug> Solve this by statically initializing the lock. Signed-off-by:
Michael Bohan <mbohan@codeaurora.org> Link: http://lkml.kernel.org/r/1363745965-23475-1-git-send-email-mbohan@codeaurora.orgSigned-off-by:
Thomas Gleixner <tglx@linutronix.de> Signed-off-by:
-
Russell King authored
commit b6c7aabd upstream. Let's do the changes properly and fix the same problem everywhere, not just for one case. Signed-off-by:
-
- 17 Apr, 2013 11 commits
-
-
Greg Kroah-Hartman authored
-
David Woodhouse authored
commit f5cf8f07 upstream. This code was broken because it assumed that all MTD devices were map-based. Disable it for now, until it can be fixed properly for the next merge window. Signed-off-by:
David Woodhouse <David.Woodhouse@intel.com> Signed-off-by:
-
Hayes Wang authored
commit e2409d83 upstream. It would cause no link after suspending or shutdowning when the nic changes the speed to 10M and connects to a link partner which forces the speed to 100M. Check the link partner ability to determine which speed to set. Signed-off-by:
Hayes Wang <hayeswang@realtek.com> Acked-by:
Francois Romieu <romieu@fr.zoreil.com> Signed-off-by:
David S. Miller <davem@davemloft.net> Signed-off-by:
-
Linus Torvalds authored
commit a49b7e82 upstream. Anatol Pomozov identified a race condition that hits module unloading and re-loading. To quote Anatol: "This is a race codition that exists between kset_find_obj() and kobject_put(). kset_find_obj() might return kobject that has refcount equal to 0 if this kobject is freeing by kobject_put() in other thread. Here is timeline for the crash in case if kset_find_obj() searches for an object tht nobody holds and other thread is doing kobject_put() on the same kobject: THREAD A (calls kset_find_obj()) THREAD B (calls kobject_put()) splin_lock() atomic_dec_return(kobj->kref), counter gets zero here ... starts kobject cleanup .... spin_lock() // WAIT thread A in kobj_kset_leave() iterate over kset->list atomic_inc(kobj->kref) (counter becomes 1) spin_unlock() spin_lock() // taken // it does not know that thread A increased counter so it remove obj from list spin_unlock() vfree(module) // frees module object with containing kobj // kobj points to freed memory area!! kobject_put(kobj) // OOPS!!!! The race above happens because module.c tries to use kset_find_obj() when somebody unloads module. The module.c code was introduced in commit 6494a93d" Anatol supplied a patch specific for module.c that worked around the problem by simply not using kset_find_obj() at all, but rather than make a local band-aid, this just fixes kset_find_obj() to be thread-safe using the proper model of refusing the get a new reference if the refcount has already dropped to zero. See examples of this proper refcount handling not only in the kref documentation, but in various other equivalent uses of this pattern by grepping for atomic_inc_not_zero(). [ Side note: the module race does indicate that module loading and unloading is not properly serialized wrt sysfs information using the module mutex. That may require further thought, but this is the correct fix at the kobject layer regardless. ] Reported-analyzed-and-tested-by:
Anatol Pomozov <anatol.pomozov@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by:
-
Linus Torvalds authored
commit 9c603e53 upstream. Sasha Levin has been running trinity in a KVM tools guest, and was able to trigger the BUG_ON() at arch/x86/mm/pat.c:279 (verifying the range of the memory type). The call trace showed that it was mtdchar_mmap() that created an invalid remap_pfn_range(). The problem is that mtdchar_mmap() does various really odd and subtle things with the vma page offset etc, and uses the wrong types (and the wrong overflow) detection for it. For example, the page offset may well be 32-bit on a 32-bit architecture, but after shifting it up by PAGE_SHIFT, we need to use a potentially 64-bit resource_size_t to correctly hold the full value. Also, we need to check that the vma length plus offset doesn't overflow before we check that it is smaller than the length of the mtdmap region. This fixes things up and tries to make the code a bit easier to read. Reported-and-tested-by:
Sasha Levin <levinsasha928@gmail.com> Acked-by:
Suresh Siddha <suresh.b.siddha@intel.com> Acked-by:
Artem Bityutskiy <dedekind1@gmail.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: linux-mtd@lists.infradead.org Signed-off-by:
-
Boris Ostrovsky authored
commit 511ba86e upstream. Invoking arch_flush_lazy_mmu_mode() results in calls to preempt_enable()/disable() which may have performance impact. Since lazy MMU is not used on bare metal we can patch away arch_flush_lazy_mmu_mode() so that it is never called in such environment. [ hpa: the previous patch "Fix vmalloc_fault oops during lazy MMU updates" may cause a minor performance regression on bare metal. This patch resolves that performance regression. It is somewhat unclear to me if this is a good -stable candidate. ] Signed-off-by:
Boris Ostrovsky <boris.ostrovsky@oracle.com> Link: http://lkml.kernel.org/r/1364045796-10720-2-git-send-email-konrad.wilk@oracle.comTested-by:
Josh Boyer <jwboyer@redhat.com> Tested-by:
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by:
Borislav Petkov <bp@suse.de> Signed-off-by:
H. Peter Anvin <hpa@linux.intel.com> Signed-off-by:
-
Samu Kallio authored
commit 1160c277 upstream. In paravirtualized x86_64 kernels, vmalloc_fault may cause an oops when lazy MMU updates are enabled, because set_pgd effects are being deferred. One instance of this problem is during process mm cleanup with memory cgroups enabled. The chain of events is as follows: - zap_pte_range enables lazy MMU updates - zap_pte_range eventually calls mem_cgroup_charge_statistics, which accesses the vmalloc'd mem_cgroup per-cpu stat area - vmalloc_fault is triggered which tries to sync the corresponding PGD entry with set_pgd, but the update is deferred - vmalloc_fault oopses due to a mismatch in the PUD entries The OOPs usually looks as so: ------------[ cut here ]------------ kernel BUG at arch/x86/mm/fault.c:396! invalid opcode: 0000 [#1] SMP .. snip .. CPU 1 Pid: 10866, comm: httpd Not tainted 3.6.10-4.fc18.x86_64 #1 RIP: e030:[<ffffffff816271bf>] [<ffffffff816271bf>] vmalloc_fault+0x11f/0x208 .. snip .. Call Trace: [<ffffffff81627759>] do_page_fault+0x399/0x4b0 [<ffffffff81004f4c>] ? xen_mc_extend_args+0xec/0x110 [<ffffffff81624065>] page_fault+0x25/0x30 [<ffffffff81184d03>] ? mem_cgroup_charge_statistics.isra.13+0x13/0x50 [<ffffffff81186f78>] __mem_cgroup_uncharge_common+0xd8/0x350 [<ffffffff8118aac7>] mem_cgroup_uncharge_page+0x57/0x60 [<ffffffff8115fbc0>] page_remove_rmap+0xe0/0x150 [<ffffffff8115311a>] ? vm_normal_page+0x1a/0x80 [<ffffffff81153e61>] unmap_single_vma+0x531/0x870 [<ffffffff81154962>] unmap_vmas+0x52/0xa0 [<ffffffff81007442>] ? pte_mfn_to_pfn+0x72/0x100 [<ffffffff8115c8f8>] exit_mmap+0x98/0x170 [<ffffffff810050d9>] ? __raw_callee_save_xen_pmd_val+0x11/0x1e [<ffffffff81059ce3>] mmput+0x83/0xf0 [<ffffffff810624c4>] exit_mm+0x104/0x130 [<ffffffff8106264a>] do_exit+0x15a/0x8c0 [<ffffffff810630ff>] do_group_exit+0x3f/0xa0 [<ffffffff81063177>] sys_exit_group+0x17/0x20 [<ffffffff8162bae9>] system_call_fastpath+0x16/0x1b Calling arch_flush_lazy_mmu_mode immediately after set_pgd makes the changes visible to the consistency checks. RedHat-Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=914737Tested-by:
Krishna Raman <kraman@redhat.com> Signed-off-by:
Samu Kallio <samu.kallio@aberdeencloud.com> Link: http://lkml.kernel.org/r/1364045796-10720-1-git-send-email-konrad.wilk@oracle.comTested-by:
-
Thomas Gleixner authored
commit a1cbcaa9 upstream. The sched_clock_remote() implementation has the following inatomicity problem on 32bit systems when accessing the remote scd->clock, which is a 64bit value. CPU0 CPU1 sched_clock_local() sched_clock_remote(CPU0) ... remote_clock = scd[CPU0]->clock read_low32bit(scd[CPU0]->clock) cmpxchg64(scd->clock,...) read_high32bit(scd[CPU0]->clock) While the update of scd->clock is using an atomic64 mechanism, the readout on the remote cpu is not, which can cause completely bogus readouts. It is a quite rare problem, because it requires the update to hit the narrow race window between the low/high readout and the update must go across the 32bit boundary. The resulting misbehaviour is, that CPU1 will see the sched_clock on CPU1 ~4 seconds ahead of it's own and update CPU1s sched_clock value to this bogus timestamp. This stays that way due to the clamping implementation for about 4 seconds until the synchronization with CLOCK_MONOTONIC undoes the problem. The issue is hard to observe, because it might only result in a less accurate SCHED_OTHER timeslicing behaviour. To create observable damage on realtime scheduling classes, it is necessary that the bogus update of CPU1 sched_clock happens in the context of an realtime thread, which then gets charged 4 seconds of RT runtime, which results in the RT throttler mechanism to trigger and prevent scheduling of RT tasks for a little less than 4 seconds. So this is quite unlikely as well. The issue was quite hard to decode as the reproduction time is between 2 days and 3 weeks and intrusive tracing makes it less likely, but the following trace recorded with trace_clock=global, which uses sched_clock_local(), gave the final hint: <idle>-0 0d..30 400269.477150: hrtimer_cancel: hrtimer=0xf7061e80 <idle>-0 0d..30 400269.477151: hrtimer_start: hrtimer=0xf7061e80 ... irq/20-S-587 1d..32 400273.772118: sched_wakeup: comm= ... target_cpu=0 <idle>-0 0dN.30 400273.772118: hrtimer_cancel: hrtimer=0xf7061e80 What happens is that CPU0 goes idle and invokes sched_clock_idle_sleep_event() which invokes sched_clock_local() and CPU1 runs a remote wakeup for CPU0 at the same time, which invokes sched_remote_clock(). The time jump gets propagated to CPU0 via sched_remote_clock() and stays stale on both cores for ~4 seconds. There are only two other possibilities, which could cause a stale sched clock: 1) ktime_get() which reads out CLOCK_MONOTONIC returns a sporadic wrong value. 2) sched_clock() which reads the TSC returns a sporadic wrong value. #1 can be excluded because sched_clock would continue to increase for one jiffy and then go stale. #2 can be excluded because it would not make the clock jump forward. It would just result in a stale sched_clock for one jiffy. After quite some brain twisting and finding the same pattern on other traces, sched_clock_remote() remained the only place which could cause such a problem and as explained above it's indeed racy on 32bit systems. So while on 64bit systems the readout is atomic, we need to verify the remote readout on 32bit machines. We need to protect the local->clock readout in sched_clock_remote() on 32bit as well because an NMI could hit between the low and the high readout, call sched_clock_local() and modify local->clock. Thanks to Siegfried Wulsch for bearing with my debug requests and going through the tedious tasks of running a bunch of reproducer systems to generate the debug information which let me decode the issue. Reported-by:
Siegfried Wulsch <Siegfried.Wulsch@rovema.de> Acked-by:
Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304051544160.21884@ionosSigned-off-by:
-
Dave Airlie authored
commit 1baee586 upstream. Don't oops seems proper. Signed-off-by:
-
Thomas Hellstrom authored
commit 4b20db3d upstream. This function is intended to simplify locking around refcounting for objects that can be looked up from a lookup structure, and which are removed from that lookup structure in the object destructor. Operations on such objects require at least a read lock around lookup + kref_get, and a write lock around kref_put + remove from lookup structure. Furthermore, RCU implementations become extremely tricky. With a lookup followed by a kref_get_unless_zero *with return value check* locking in the kref_put path can be deferred to the actual removal from the lookup structure and RCU lookups become trivial. v2: Formatting fixes. v3: Invert the return value. Signed-off-by:
Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by:
-
Suleiman Souhlal authored
commit 5b55d708 upstream. Revert commit 62a3ddef ("vfs: fix spinning prevention in prune_icache_sb"). This commit doesn't look right: since we are looking at the tail of the list (sb->s_inode_lru.prev) if we want to skip an inode, we should put it back at the head of the list instead of the tail, otherwise we will keep spinning on it. Discovered when investigating why prune_icache_sb came top in perf reports of a swapping load. Signed-off-by:
Suleiman Souhlal <suleiman@google.com> Signed-off-by:
Hugh Dickins <hughd@google.com> Signed-off-by:
-
