| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Since VPMU code emulates RDPMC instruction with RDMSR and because hypervisor
does not emulate it there is no reason to try setting CR4's PCE bit (and the
hypervisor will warn on seeing it set).
Signed-off-by: Boris Ostrovsky <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Add PMU emulation code that runs when we are processing a PMU interrupt.
This code will allow us not to trap to hypervisor on each MSR/LVTPC access
(of which there may be quite a few in the handler).
Signed-off-by: Boris Ostrovsky <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Provide interfaces for recognizing accesses to PMU-related MSRs and
LVTPC APIC and process these accesses in Xen PMU code.
(The interrupt handler performs XENPMU_flush right away in the beginning
since no PMU emulation is available. It will be added with a later patch).
Signed-off-by: Boris Ostrovsky <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
AMD and Intel PMU register initialization and helpers that determine
whether a register belongs to PMU.
This and some of subsequent PMU emulation code is somewhat similar to
Xen's PMU implementation.
Signed-off-by: Boris Ostrovsky <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Map shared data structure that will hold CPU registers, VPMU context,
V/PCPU IDs of the CPU interrupted by PMU interrupt. Hypervisor fills
this information in its handler and passes it to the guest for further
processing.
Set up PMU VIRQ.
Now that perf infrastructure will assume that PMU is available on a PV
guest we need to be careful and make sure that accesses via RDPMC
instruction don't cause fatal traps by the hypervisor. Provide a nop
RDPMC handler.
For the same reason avoid issuing a warning on a write to APIC's LVTPC.
Both of these will be made functional in later patches.
Signed-off-by: Boris Ostrovsky <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Set Xen's PMU mode via /sys/hypervisor/pmu/pmu_mode. Add XENPMU hypercall.
Signed-off-by: Boris Ostrovsky <[email protected]>
Reviewed-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Export Xen symbols to dom0 via /proc/xen/xensyms (similar to
/proc/kallsyms).
Signed-off-by: Boris Ostrovsky <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Cleanup by removing arch/x86/xen/p2m.h as it isn't needed any more.
Most definitions in this file are used in p2m.c only. Move those into
p2m.c.
set_phys_range_identity() is already declared in
arch/x86/include/asm/xen/page.h, add __init annotation there.
MAX_REMAP_RANGES isn't used at all, just delete it.
The only define left is P2M_PER_PAGE which is moved to page.h as well.
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
64 bit pv-domains under Xen are limited to 512 GB of RAM today. The
main reason has been the 3 level p2m tree, which was replaced by the
virtual mapped linear p2m list. Parallel to the p2m list which is
being used by the kernel itself there is a 3 level mfn tree for usage
by the Xen tools and eventually for crash dump analysis. For this tree
the linear p2m list can serve as a replacement, too. As the kernel
can't know whether the tools are capable of dealing with the p2m list
instead of the mfn tree, the limit of 512 GB can't be dropped in all
cases.
This patch replaces the hard limit by a kernel parameter which tells
the kernel to obey the 512 GB limit or not. The default is selected by
a configuration parameter which specifies whether the 512 GB limit
should be active per default for domUs (domain save/restore/migration
and crash dump analysis are affected).
Memory above the domain limit is returned to the hypervisor instead of
being identity mapped, which was wrong anyway.
The kernel configuration parameter to specify the maximum size of a
domain can be deleted, as it is not relevant any more.
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Check whether the hypervisor supplied p2m list is placed at a location
which is conflicting with the target E820 map. If this is the case
relocate it to a new area unused up to now and compliant to the E820
map.
As the p2m list might by huge (up to several GB) and is required to be
mapped virtually, set up a temporary mapping for the copied list.
For pvh domains just delete the p2m related information from start
info instead of reserving the p2m memory, as we don't need it at all.
For 32 bit kernels adjust the memblock_reserve() parameters in order
to cover the page tables only. This requires to memblock_reserve() the
start_info page on it's own.
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Some special pages containing interfaces to xen are being reserved
implicitly only today. The memblock_reserve() call to reserve them is
meant to reserve the p2m list supplied by xen. It is just reserving
not only the p2m list itself, but some more pages up to the start of
the xen built page tables.
To be able to move the p2m list to another pfn range, which is needed
for support of huge RAM, this memblock_reserve() must be split up to
cover all affected reserved pages explicitly.
The affected pages are:
- start_info page
- xenstore ring (might be missing, mfn is 0 in this case)
- console ring (not for initial domain)
Signed-off-by: Juergen Gross <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
During early boot as Xen pv domain the kernel needs to map some page
tables supplied by the hypervisor read only. This is needed to be
able to relocate some data structures conflicting with the physical
memory map especially on systems with huge RAM (above 512GB).
Provide the function early_memremap_ro() to provide this read only
mapping.
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Check whether the initrd is placed at a location which is conflicting
with the target E820 map. If this is the case relocate it to a new
area unused up to now and compliant to the E820 map.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Check whether the page tables built by the domain builder are at
memory addresses which are in conflict with the target memory map.
If this is the case just panic instead of running into problems
later.
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Checks whether the pre-allocated memory of the loaded kernel is in
conflict with the target memory map. If this is the case, just panic
instead of run into problems later, as there is nothing we can do
to repair this situation.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
For being able to relocate pre-allocated data areas like initrd or
p2m list it is mandatory to find a contiguous memory area which is
not yet in use and doesn't conflict with the memory map we want to
be in effect.
In case such an area is found reserve it at once as this will be
required to be done in any case.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Provide a service routine to check a physical memory area against the
E820 map. The routine will return false if the complete area is RAM
according to the E820 map and true otherwise.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Memory pages in the initial memory setup done by the Xen hypervisor
conflicting with the target E820 map are remapped. In order to do this
those pages are counted and remapped in xen_set_identity_and_remap().
Split the counting from the remapping operation to be able to setup
the needed memory sizes in time but doing the remap operation at a
later time. This enables us to simplify the interface to
xen_set_identity_and_remap() as the number of remapped and released
pages is no longer needed here.
Finally move the remapping further down to prepare relocating
conflicting memory contents before the memory might be clobbered by
xen_set_identity_and_remap(). This requires to not destroy the Xen
E820 map when the one for the system is being constructed.
Signed-off-by: Juergen Gross <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Instead of using a function local static e820 map in xen_memory_setup()
and calling various functions in the same source with the map as a
parameter use a map directly accessible by all functions in the source.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Direct Xen to place the initial P->M table outside of the initial
mapping, as otherwise the 1G (implementation) / 2G (theoretical)
restriction on the size of the initial mapping limits the amount
of memory a domain can be handed initially.
As the initial P->M table is copied rather early during boot to
domain private memory and it's initial virtual mapping is dropped,
the easiest way to avoid virtual address conflicts with other
addresses in the kernel is to use a user address area for the
virtual address of the initial P->M table. This allows us to just
throw away the page tables of the initial mapping after the copy
without having to care about address invalidation.
It should be noted that this patch won't enable a pv-domain to USE
more than 512 GB of RAM. It just enables it to be started with a
P->M table covering more memory. This is especially important for
being able to boot a Dom0 on a system with more than 512 GB memory.
Signed-off-by: Juergen Gross <[email protected]>
Based-on-patch-by: Jan Beulich <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
In case the Xen tools indicate they don't need the p2m 3 level tree
as they support the virtual mapped linear p2m list, just omit building
the tree.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
The virtual address of the linear p2m list should be stored in the
shared info structure read by the Xen tools to be able to support
64 bit pv-domains larger than 512 GB. Additionally the linear p2m
list interface includes a generation count which is changed prior
to and after each mapping change of the p2m list. Reading the
generation count the Xen tools can detect changes of the mappings
and re-read the p2m list eventually.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Use the newest headers from the xen tree to get some new structure
layouts.
Signed-off-by: Juergen Gross <[email protected]>
Reviewed-by: David Vrabel <[email protected]>
Acked-by: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
The commit 6f6c15ef912465b3aaafe709f39bd6026a8b3e72 "xen/pvhvm: Remove
the xen_platform_pci int." makes the x86 version of
xen_pci_platform_unplug static.
Therefore we don't need anymore to define a dummy xen_pci_platform_unplug
for ARM.
Signed-off-by: Julien Grall <[email protected]>
Signed-off-by: Stefano Stabellini <[email protected]>
|
|
Currently, the event channel rebind code is gated with the presence of
the vector callback.
The virtual interrupt controller on ARM has the concept of per-CPU
interrupt (PPI) which allow us to support per-VCPU event channel.
Therefore there is no need of vector callback for ARM.
Xen is already using a free PPI to notify the guest VCPU of an event.
Furthermore, the xen code initialization in Linux (see
arch/arm/xen/enlighten.c) is requesting correctly a per-CPU IRQ.
Introduce new helper xen_support_evtchn_rebind to allow architecture
decide whether rebind an event is support or not. It will always return
true on ARM and keep the same behavior on x86.
This is also allow us to drop the usage of xen_have_vector_callback
entirely in the ARM code.
Signed-off-by: Julien Grall <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
Note: This patch is based on original work of Arianna's internship for
GNOME's Outreach Program for Women.
Only one hardware queue is used now, so there is no significant
performance change
The legacy non-mq code is deleted completely which is the same as other
drivers like virtio, mtip, and nvme.
Also dropped one unnecessary holding of info->io_lock when calling
blk_mq_stop_hw_queues().
Signed-off-by: Arianna Avanzini <[email protected]>
Signed-off-by: Bob Liu <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Acked-by: Jens Axboe <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
This code is used only when CONFIG_PREEMPT=n and only in non-atomic
context: xen_in_preemptible_hcall is set only in
privcmd_ioctl_hypercall(). Thus preempt_count is zero and
should_resched() is equal to need_resched().
Signed-off-by: Konstantin Khlebnikov <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
xen_has_pv_devices() has no parameters, so use the normal void
parameter convention to make it match the prototype in the header file
include/xen/platform_pci.h.
Signed-off-by: Colin Ian King <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
|
|
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC fixes from Olof Johansson:
"A smallish batch of fixes, a little more than expected this late, but
all fixes are contained to their platforms and seem reasonably low
risk:
- a somewhat large SMP fix for ux500 that still seemed warranted to
include here
- OMAP DT fixes for pbias regulator specification that broke due to
some DT reshuffling
- PCIe IRQ routing bugfix for i.MX
- networking fixes for keystone
- runtime PM for OMAP GPMC
- a couple of error path bug fixes for exynos"
* tag 'armsoc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
ARM: dts: keystone: Fix the mdio bindings by moving it to soc specific file
ARM: dts: keystone: fix the clock node for mdio
memory: omap-gpmc: Don't try to save uninitialized GPMC context
ARM: imx6: correct i.MX6 PCIe interrupt routing
ARM: ux500: add an SMP enablement type and move cpu nodes
ARM: dts: dra7: Fix broken pbias device creation
ARM: dts: OMAP5: Fix broken pbias device creation
ARM: dts: OMAP4: Fix broken pbias device creation
ARM: dts: omap243x: Fix broken pbias device creation
ARM: EXYNOS: fix double of_node_put() on error path
ARM: EXYNOS: Fix potentian kfree() of ro memory
|
|
Pull MIPS bugfix from Ralf Baechle:
"Only a single MIPS fix - the math when invoking syscall_trace_enter
was wrong"
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
MIPS: Fix seccomp syscall argument for MIPS64
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Merge x86 fixes from Ingo Molnar:
"Two followup fixes related to the previous LDT fix"
Also applied a further FPU emulation fix from Andy Lutomirski to the
branch before actually merging it.
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
x86/ldt: Further fix FPU emulation
x86/ldt: Correct FPU emulation access to LDT
x86/ldt: Correct LDT access in single stepping logic
|
|
The previous fix confused a selector with a segment prefix. Fix it.
Compile-tested only.
Cc: [email protected]
Cc: Juergen Gross <[email protected]>
Reported-by: Linus Torvalds <[email protected]>
Fixes: 4809146b86c3 ("x86/ldt: Correct FPU emulation access to LDT")
Signed-off-by: Andy Lutomirski <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
fuse_dev_ioctl() performed fuse_get_dev() on a user-supplied fd,
leading to a type confusion issue. Fix it by checking file->f_op.
Signed-off-by: Jann Horn <[email protected]>
Acked-by: Miklos Szeredi <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone into fixes
ARM: Couple of Keysyone MDIO DTS fixes for 4.2-rc6+
These are necessary to get the NIC card working on all Keystone
EVMs. Couple of boards are broken without these two fixes.
* tag 'keystone-dts-late-fixes-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone:
ARM: dts: keystone: Fix the mdio bindings by moving it to soc specific file
ARM: dts: keystone: fix the clock node for mdio
Signed-off-by: Olof Johansson <[email protected]>
|
|
Commit 4c21b8fd8f14 ("MIPS: seccomp: Handle indirect system calls (o32)")
fixed indirect system calls on O32 but it also introduced a bug for MIPS64
where it erroneously modified the v0 (syscall) register with the assumption
that the sycall offset hasn't been taken into consideration. This breaks
seccomp on MIPS64 n64 and n32 ABIs. We fix this by replacing the addition
with a move instruction.
Fixes: 4c21b8fd8f14 ("MIPS: seccomp: Handle indirect system calls (o32)")
Cc: <[email protected]> # 3.15+
Reviewed-by: James Hogan <[email protected]>
Signed-off-by: Markos Chandras <[email protected]>
Cc: [email protected]
Patchwork: https://patchwork.linux-mips.org/patch/10951/
Signed-off-by: Ralf Baechle <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI fixes from James Bottomley:
"This has two libfc fixes for bugs causing rare crashes, one iscsi fix
for a potential hang on shutdown, and a fix for an I/O blocksize issue
which caused a regression"
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
sd: Fix maximum I/O size for BLOCK_PC requests
libfc: Fix fc_fcp_cleanup_each_cmd()
libfc: Fix fc_exch_recv_req() error path
libiscsi: Fix host busy blocking during connection teardown
|
|
Pull KVM fixes from Paolo Bonzini:
"Just two very small & simple patches"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86: Use adjustment in guest cycles when handling MSR_IA32_TSC_ADJUST
KVM: x86: zero IDT limit on entry to SMM
|
|
Merge fixes from Andrew Morton:
"11 fixes"
* emailed patches from Andrew Morton <[email protected]>:
Update maintainers for DRM STI driver
mm: cma: mark cma_bitmap_maxno() inline in header
zram: fix pool name truncation
memory-hotplug: fix wrong edge when hot add a new node
.mailmap: Andrey Ryabinin has moved
ipc/sem.c: update/correct memory barriers
mm/hwpoison: fix panic due to split huge zero page
ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()
ipc,sem: fix use after free on IPC_RMID after a task using same semaphore set exits
mm/hwpoison: fix fail isolate hugetlbfs page w/ refcount held
mm/hwpoison: fix page refcount of unknown non LRU page
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux
Pull clock fix from Stephen Boyd:
"A one-liner for a regression found in the PXA clock driver"
* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
clk: pxa: pxa3xx: fix CKEN register access
|
|
Add Vincent Abriou and myself as maintainers.
Signed-off-by: Benjamin Gaignard <[email protected]>
Cc: Vincent Abriou <[email protected]>
Cc: Dave Airlie <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
cma_bitmap_maxno() was marked as static and not static inline, which can
cause warnings about this function not being used if this file is included
in a file that does not call that function, and violates the conventions
used elsewhere. The two options are to move the function implementation
back to mm/cma.c or make it inline here, and it's simple enough for the
latter to make sense.
Signed-off-by: Gregory Fong <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Sasha Levin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
zram_meta_alloc() constructs a pool name for zs_create_pool() call as
snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
However, it defines pool name buffer to be only 8 bytes long (minus
trailing zero), which means that we can have only 1000 pool names: zram0
-- zram999.
With CONFIG_ZSMALLOC_STAT enabled an attempt to create a device zram1000
can fail if device zram100 already exists, because snprintf() will
truncate new pool name to zram100 and pass it debugfs_create_dir(),
causing:
debugfs dir <zram100> creation failed
zram: Error creating memory pool
... and so on.
Fix it by passing zram->disk->disk_name to zram_meta_alloc() instead of
divice_id. We construct zram%d name earlier and keep it as a ->disk_name,
no need to snprintf() it again.
Signed-off-by: Sergey Senozhatsky <[email protected]>
Cc: Minchan Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
When we add a new node, the edge of memory may be wrong.
e.g. system has 4 nodes, and node3 is movable, node3 mem:[24G-32G],
1. hotremove the node3,
2. then hotadd node3 with a part of memory, mem:[26G-30G],
3. call hotadd_new_pgdat()
free_area_init_node()
get_pfn_range_for_nid()
4. it will return wrong start_pfn and end_pfn, because we have not
update the memblock.
This patch also fixes a BUG_ON during hot-addition, please see
http://marc.info/?l=linux-kernel&m=142961156129456&w=2
Signed-off-by: Xishi Qiu <[email protected]>
Cc: Yasuaki Ishimatsu <[email protected]>
Cc: Kamezawa Hiroyuki <[email protected]>
Cc: Taku Izumi <[email protected]>
Cc: Tang Chen <[email protected]>
Cc: Gu Zheng <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Update my email address.
Signed-off-by: Andrey Ryabinin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
sem_lock() did not properly pair memory barriers:
!spin_is_locked() and spin_unlock_wait() are both only control barriers.
The code needs an acquire barrier, otherwise the cpu might perform read
operations before the lock test.
As no primitive exists inside <include/spinlock.h> and since it seems
noone wants another primitive, the code creates a local primitive within
ipc/sem.c.
With regards to -stable:
The change of sem_wait_array() is a bugfix, the change to sem_lock() is a
nop (just a preprocessor redefinition to improve the readability). The
bugfix is necessary for all kernels that use sem_wait_array() (i.e.:
starting from 3.10).
Signed-off-by: Manfred Spraul <[email protected]>
Reported-by: Oleg Nesterov <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Cc: "Paul E. McKenney" <[email protected]>
Cc: Kirill Tkhai <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Josh Poimboeuf <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: <[email protected]> [3.10+]
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Bug:
------------[ cut here ]------------
kernel BUG at mm/huge_memory.c:1957!
invalid opcode: 0000 [#1] SMP
Modules linked in: snd_hda_codec_hdmi i915 rpcsec_gss_krb5 snd_hda_codec_realtek snd_hda_codec_generic nfsv4 dns_re
CPU: 2 PID: 2576 Comm: test_huge Not tainted 4.2.0-rc5-mm1+ #27
Hardware name: Dell Inc. OptiPlex 7020/0F5C5X, BIOS A03 01/08/2015
task: ffff880204e3d600 ti: ffff8800db16c000 task.ti: ffff8800db16c000
RIP: split_huge_page_to_list+0xdb/0x120
Call Trace:
memory_failure+0x32e/0x7c0
madvise_hwpoison+0x8b/0x160
SyS_madvise+0x40/0x240
? do_page_fault+0x37/0x90
entry_SYSCALL_64_fastpath+0x12/0x71
Code: ff f0 41 ff 4c 24 30 74 0d 31 c0 48 83 c4 08 5b 41 5c 41 5d c9 c3 4c 89 e7 e8 e2 58 fd ff 48 83 c4 08 31 c0
RIP split_huge_page_to_list+0xdb/0x120
RSP <ffff8800db16fde8>
---[ end trace aee7ce0df8e44076 ]---
Testcase:
#define _GNU_SOURCE
#include <stdlib.h>
#include <stdio.h>
#include <sys/mman.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
#include <errno.h>
#include <string.h>
#define MB 1024*1024
int main(void)
{
char *mem;
posix_memalign((void **)&mem, 2 * MB, 200 * MB);
madvise(mem, 200 * MB, MADV_HWPOISON);
free(mem);
return 0;
}
Huge zero page is allocated if page fault w/o FAULT_FLAG_WRITE flag.
The get_user_pages_fast() which called in madvise_hwpoison() will get
huge zero page if the page is not allocated before. Huge zero page is a
tranparent huge page, however, it is not an anonymous page.
memory_failure will split the huge zero page and trigger
BUG_ON(is_huge_zero_page(page));
After commit 98ed2b0052e6 ("mm/memory-failure: give up error handling
for non-tail-refcounted thp"), memory_failure will not catch non anon
thp from madvise_hwpoison path and this bug occur.
Fix it by catching non anon thp in memory_failure in order to not split
huge zero page in madvise_hwpoison path.
After this patch:
Injecting memory failure for page 0x202800 at 0x7fd8ae800000
MCE: 0x202800: non anonymous thp
[...]
[[email protected]: remove second split, per Wanpeng]
Signed-off-by: Wanpeng Li <[email protected]>
Acked-by: Naoya Horiguchi <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
After we acquire the sma->sem_perm lock in exit_sem(), we are protected
against a racing IPC_RMID operation. Also at that point, we are the last
user of sem_undo_list. Therefore it isn't required that we acquire or use
ulp->lock.
Signed-off-by: Herton R. Krzesinski <[email protected]>
Acked-by: Manfred Spraul <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Rafael Aquini <[email protected]>
CC: Aristeu Rozanski <[email protected]>
Cc: David Jeffery <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
set exits
The current semaphore code allows a potential use after free: in
exit_sem we may free the task's sem_undo_list while there is still
another task looping through the same semaphore set and cleaning the
sem_undo list at freeary function (the task called IPC_RMID for the same
semaphore set).
For example, with a test program [1] running which keeps forking a lot
of processes (which then do a semop call with SEM_UNDO flag), and with
the parent right after removing the semaphore set with IPC_RMID, and a
kernel built with CONFIG_SLAB, CONFIG_SLAB_DEBUG and
CONFIG_DEBUG_SPINLOCK, you can easily see something like the following
in the kernel log:
Slab corruption (Not tainted): kmalloc-64 start=ffff88003b45c1c0, len=64
000: 6b 6b 6b 6b 6b 6b 6b 6b 00 6b 6b 6b 6b 6b 6b 6b kkkkkkkk.kkkkkkk
010: ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
Prev obj: start=ffff88003b45c180, len=64
000: 00 00 00 00 ad 4e ad de ff ff ff ff 5a 5a 5a 5a .....N......ZZZZ
010: ff ff ff ff ff ff ff ff c0 fb 01 37 00 88 ff ff ...........7....
Next obj: start=ffff88003b45c200, len=64
000: 00 00 00 00 ad 4e ad de ff ff ff ff 5a 5a 5a 5a .....N......ZZZZ
010: ff ff ff ff ff ff ff ff 68 29 a7 3c 00 88 ff ff ........h).<....
BUG: spinlock wrong CPU on CPU#2, test/18028
general protection fault: 0000 [#1] SMP
Modules linked in: 8021q mrp garp stp llc nf_conntrack_ipv4 nf_defrag_ipv4 ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc ppdev input_leds joydev parport_pc parport floppy serio_raw virtio_balloon virtio_rng virtio_console virtio_net iosf_mbi crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcspkr qxl ttm drm_kms_helper drm snd_hda_codec_generic i2c_piix4 snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm snd_timer snd soundcore crc32c_intel virtio_pci virtio_ring virtio pata_acpi ata_generic [last unloaded: speedstep_lib]
CPU: 2 PID: 18028 Comm: test Not tainted 4.2.0-rc5+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
RIP: spin_dump+0x53/0xc0
Call Trace:
spin_bug+0x30/0x40
do_raw_spin_unlock+0x71/0xa0
_raw_spin_unlock+0xe/0x10
freeary+0x82/0x2a0
? _raw_spin_lock+0xe/0x10
semctl_down.clone.0+0xce/0x160
? __do_page_fault+0x19a/0x430
? __audit_syscall_entry+0xa8/0x100
SyS_semctl+0x236/0x2c0
? syscall_trace_leave+0xde/0x130
entry_SYSCALL_64_fastpath+0x12/0x71
Code: 8b 80 88 03 00 00 48 8d 88 60 05 00 00 48 c7 c7 a0 2c a4 81 31 c0 65 8b 15 eb 40 f3 7e e8 08 31 68 00 4d 85 e4 44 8b 4b 08 74 5e <45> 8b 84 24 88 03 00 00 49 8d 8c 24 60 05 00 00 8b 53 04 48 89
RIP [<ffffffff810d6053>] spin_dump+0x53/0xc0
RSP <ffff88003750fd68>
---[ end trace 783ebb76612867a0 ]---
NMI watchdog: BUG: soft lockup - CPU#3 stuck for 22s! [test:18053]
Modules linked in: 8021q mrp garp stp llc nf_conntrack_ipv4 nf_defrag_ipv4 ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc ppdev input_leds joydev parport_pc parport floppy serio_raw virtio_balloon virtio_rng virtio_console virtio_net iosf_mbi crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcspkr qxl ttm drm_kms_helper drm snd_hda_codec_generic i2c_piix4 snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm snd_timer snd soundcore crc32c_intel virtio_pci virtio_ring virtio pata_acpi ata_generic [last unloaded: speedstep_lib]
CPU: 3 PID: 18053 Comm: test Tainted: G D 4.2.0-rc5+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
RIP: native_read_tsc+0x0/0x20
Call Trace:
? delay_tsc+0x40/0x70
__delay+0xf/0x20
do_raw_spin_lock+0x96/0x140
_raw_spin_lock+0xe/0x10
sem_lock_and_putref+0x11/0x70
SYSC_semtimedop+0x7bf/0x960
? handle_mm_fault+0xbf6/0x1880
? dequeue_task_fair+0x79/0x4a0
? __do_page_fault+0x19a/0x430
? kfree_debugcheck+0x16/0x40
? __do_page_fault+0x19a/0x430
? __audit_syscall_entry+0xa8/0x100
? do_audit_syscall_entry+0x66/0x70
? syscall_trace_enter_phase1+0x139/0x160
SyS_semtimedop+0xe/0x10
SyS_semop+0x10/0x20
entry_SYSCALL_64_fastpath+0x12/0x71
Code: 47 10 83 e8 01 85 c0 89 47 10 75 08 65 48 89 3d 1f 74 ff 7e c9 c3 0f 1f 44 00 00 55 48 89 e5 e8 87 17 04 00 66 90 c9 c3 0f 1f 00 <55> 48 89 e5 0f 31 89 c1 48 89 d0 48 c1 e0 20 89 c9 48 09 c8 c9
Kernel panic - not syncing: softlockup: hung tasks
I wasn't able to trigger any badness on a recent kernel without the
proper config debugs enabled, however I have softlockup reports on some
kernel versions, in the semaphore code, which are similar as above (the
scenario is seen on some servers running IBM DB2 which uses semaphore
syscalls).
The patch here fixes the race against freeary, by acquiring or waiting
on the sem_undo_list lock as necessary (exit_sem can race with freeary,
while freeary sets un->semid to -1 and removes the same sem_undo from
list_proc or when it removes the last sem_undo).
After the patch I'm unable to reproduce the problem using the test case
[1].
[1] Test case used below:
#include <stdio.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/sem.h>
#include <sys/wait.h>
#include <stdlib.h>
#include <time.h>
#include <unistd.h>
#include <errno.h>
#define NSEM 1
#define NSET 5
int sid[NSET];
void thread()
{
struct sembuf op;
int s;
uid_t pid = getuid();
s = rand() % NSET;
op.sem_num = pid % NSEM;
op.sem_op = 1;
op.sem_flg = SEM_UNDO;
semop(sid[s], &op, 1);
exit(EXIT_SUCCESS);
}
void create_set()
{
int i, j;
pid_t p;
union {
int val;
struct semid_ds *buf;
unsigned short int *array;
struct seminfo *__buf;
} un;
/* Create and initialize semaphore set */
for (i = 0; i < NSET; i++) {
sid[i] = semget(IPC_PRIVATE , NSEM, 0644 | IPC_CREAT);
if (sid[i] < 0) {
perror("semget");
exit(EXIT_FAILURE);
}
}
un.val = 0;
for (i = 0; i < NSET; i++) {
for (j = 0; j < NSEM; j++) {
if (semctl(sid[i], j, SETVAL, un) < 0)
perror("semctl");
}
}
/* Launch threads that operate on semaphore set */
for (i = 0; i < NSEM * NSET * NSET; i++) {
p = fork();
if (p < 0)
perror("fork");
if (p == 0)
thread();
}
/* Free semaphore set */
for (i = 0; i < NSET; i++) {
if (semctl(sid[i], NSEM, IPC_RMID))
perror("IPC_RMID");
}
/* Wait for forked processes to exit */
while (wait(NULL)) {
if (errno == ECHILD)
break;
};
}
int main(int argc, char **argv)
{
pid_t p;
srand(time(NULL));
while (1) {
p = fork();
if (p < 0) {
perror("fork");
exit(EXIT_FAILURE);
}
if (p == 0) {
create_set();
goto end;
}
/* Wait for forked processes to exit */
while (wait(NULL)) {
if (errno == ECHILD)
break;
};
}
end:
return 0;
}
[[email protected]: use normal comment layout]
Signed-off-by: Herton R. Krzesinski <[email protected]>
Acked-by: Manfred Spraul <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Rafael Aquini <[email protected]>
CC: Aristeu Rozanski <[email protected]>
Cc: David Jeffery <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|
|
Hugetlbfs pages will get a refcount in get_any_page() or
madvise_hwpoison() if soft offlining through madvise. The refcount which
is held by the soft offline path should be released if we fail to isolate
hugetlbfs pages.
Fix it by reducing the refcount for both isolation success and failure.
Signed-off-by: Wanpeng Li <[email protected]>
Acked-by: Naoya Horiguchi <[email protected]>
Cc: <[email protected]> [3.9+]
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
|