When Linux runs as a guest VM in Hyper-V and Hyper-V adds the virtual PCI
bus to the guest, Hyper-V always provides unique PCI domain.
commit 4a9b0933bdfc ("PCI: hv: Use device serial number as PCI domain")
overrode unique domain with the serial number of the first device added to
the virtual PCI bus.
The reason for that patch was to have a consistent and short name for the
device, but Hyper-V doesn't provide unique serial numbers. Using non-unique
serial numbers as domain IDs leads to duplicate device addresses, which
causes PCI bus registration to fail.
commit 0c195567a8f6 ("netvsc: transparent VF management") avoids the need
for commit 4a9b0933bdfc ("PCI: hv: Use device serial number as PCI
domain"). When scripts were used to configure VF devices, the name of
the VF needed to be consistent and short, but with commit 0c195567a8f6
("netvsc: transparent VF management") all the setup is done in the kernel,
and we do not need to maintain consistent name.
Revert commit 4a9b0933bdfc ("PCI: hv: Use device serial number as PCI
domain") so we can reliably support multiple devices being assigned to
a guest.
Tag the patch for stable kernels containing commit 0c195567a8f6
("netvsc: transparent VF management").
Fixes: 4a9b0933bdfc ("PCI: hv: Use device serial number as PCI domain") Signed-off-by: Sridhar Pitchai <sridhar.pitchai@microsoft.com>
[lorenzo.pieralisi@arm.com: trimmed commit log] Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: stable@vger.kernel.org # v4.14+ Reviewed-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The erratum and workaround are described by BCM5300X-ES300-RDS.pdf as
below.
R10: PCIe Transactions Periodically Fail
Description: The BCM5300X PCIe does not maintain transaction ordering.
This may cause PCIe transaction failure.
Fix Comment: Add a dummy PCIe configuration read after a PCIe
configuration write to ensure PCIe configuration access
ordering. Set ES bit of CP0 configu7 register to enable
sync function so that the sync instruction is functional.
Resolution: hndpci.c: extpci_write_config()
hndmips.c: si_mips_init()
mipsinc.h CONF7_ES
This is fixed by the CFE MIPS bcmsi chipset driver also for BCM47XX.
Also the dummy PCIe configuration read is already implemented in the
Linux BCMA driver.
Enable ExternalSync in Config7 when CONFIG_BCMA_DRIVER_PCI_HOSTMODE=y
too so that the sync instruction is externalised.
The "sector is in requested range" test used to determine whether
sectors should be re-locked or not is done on a variable that is reset
everytime we cross a chip boundary, which can lead to some blocks being
re-locked while the caller expect them to be unlocked.
Fix the check to make sure this cannot happen.
cfi_ppb_unlock() tries to relock all sectors that were locked before
unlocking the whole chip.
This locking used the chip start address + the FULL offset from the
first flash chip, thereby forming an illegal address. Fix that by using
the chip offset(adr).
do_ppb_xxlock() fails to add chip->start when querying for lock status
(and chip_ready test), which caused false status reports.
Fix that by adding adr += chip->start and adjust call sites
accordingly.
For the word write it is checked if the chip has the correct value.
But it is not checked for the write buffer as only checked if ready.
To make sure for the write buffer change to check the value.
It is enough as this patch is only checking the last written word.
Since it is described by data sheets to check the operation status.
Signed-off-by: Tokunori Ikegami <ikegami@allied-telesis.co.jp> Reviewed-by: Joakim Tjernlund <Joakim.Tjernlund@infinera.com> Cc: Chris Packham <chris.packham@alliedtelesis.co.nz> Cc: Brian Norris <computersforpeace@gmail.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Boris Brezillon <boris.brezillon@free-electrons.com> Cc: Marek Vasut <marek.vasut@gmail.com> Cc: Richard Weinberger <richard@nod.at> Cc: Cyrille Pitchen <cyrille.pitchen@wedev4u.fr> Cc: linux-mtd@lists.infradead.org Cc: stable@vger.kernel.org Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The use of -EAGAIN in rpcrdma_convert_iovs() is a latent bug: the
transport never calls xprt_write_space() when more pages become
available. -ENOBUFS will trigger the correct "delay briefly and call
again" logic.
Fixes: 7a89f9c626e3 ("xprtrdma: Honor ->send_request API contract") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: stable@vger.kernel.org # 4.8+ Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The following code fails to allocate a buffer for the
tail address that the hardware DMAs into when the user
context DMA_RTAIL is set.
if (HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
rcd->rcvhdrtail_kvaddr = dma_zalloc_coherent(
&dd->pcidev->dev, PAGE_SIZE, &dma_hdrqtail,
gfp_flags);
if (!rcd->rcvhdrtail_kvaddr)
goto bail_free;
rcd->rcvhdrqtailaddr_dma = dma_hdrqtail;
}
So the rcvhdrtail_kvaddr would then be NULL.
The mmap logic fails to check for a NULL rcvhdrtail_kvaddr.
The fix is to test for both user and kernel DMA_TAIL options
during the allocation as well as testing for a NULL
rcvhdrtail_kvaddr during the mmap processing.
Additionally, all downstream testing of the capmask for DMA_RTAIL
have been eliminated in favor of testing rcvhdrtail_kvaddr.
Cc: <stable@vger.kernel.org> # 4.9.x Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
All threads queuing CQ entries on different CQs are unnecessarily
synchronized by a spin lock to check if the CQ kthread worker hasn't
been destroyed before queuing an CQ entry.
The lock used in 6efaf10f163d ("IB/rdmavt: Avoid queuing work into a
destroyed cq kthread worker") is a device global lock and will have
poor performance at scale as completions are entered from a large
number of CPUs.
Convert to use RCU where the read side of RCU is rvt_cq_enter() to
determine that the worker is alive prior to triggering the
completion event.
Apply write side RCU semantics in rvt_driver_cq_init() and
rvt_cq_exit().
Fixes: 6efaf10f163d ("IB/rdmavt: Avoid queuing work into a destroyed cq kthread worker") Cc: <stable@vger.kernel.org> # 4.14.x Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
User send context integrity bits are cleared before the context is
disabled. If the send context is still processing data, any packets
that need those integrity bits will cause an error and halt the send
context.
During the disable handling, the driver waits for the context to drain.
If the context is halted, the driver will eventually timeout because
the context won't drain and then incorrectly bounce the link.
Reorder the bit clearing and the context disable.
Examine the software state and send context status as well as the
egress status to determine if a send context is in the halted state.
Promote the check macros to static functions for consistency with the
new check and to follow kernel style.
Remove an unused define that refers to the egress timeout.
Cc: <stable@vger.kernel.org> # 4.9.x Reviewed-by: Mitko Haralanov <mitko.haralanov@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There are config dependent code paths that expose panics in unload
paths both in this file and in debugfs_remove_recursive() because
CONFIG_FAULT_INJECTION and CONFIG_FAULT_INJECTION_DEBUG_FS can be
set independently.
Having CONFIG_FAULT_INJECTION set and CONFIG_FAULT_INJECTION_DEBUG_FS
reset causes fault_create_debugfs_attr() to return an error.
The debugfs.c routines tolerate failures, but the module unload panics
dereferencing a NULL in the two exit routines. If that is fixed, the
dir passed to debugfs_remove_recursive comes from a memory location
that was freed and potentially reused causing a segfault or corrupting
memory.
Fix by insuring that upon failure from fault_create_debugfs_attr() the
parent pointer for the routines is always set to NULL and guards added
in the exit routines to insure that debugfs_remove_recursive() is not
called when when the parent pointer is NULL.
Fixes: 0181ce31b260 ("IB/hfi1: Add receive fault injection feature") Cc: <stable@vger.kernel.org> # 4.14.x Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The code calls dma_sync on login_tx_desc->dma_addr prior to initializing it
with dma-mapped address.
login_tx_desc is a part of iser_conn structure and is used only once
during login negotiation, so the issue is fixed by eliminating
dma_sync call for this buffer using a special case routine.
Cc: <stable@vger.kernel.org> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Don Dutile <ddutile@redhat.com> Signed-off-by: Alex Estrin <alex.estrin@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
On fatal error the driver simulates CQE's for ULPs that rely on
completion of all their posted work-request.
For the GSI traffic, the mlx5 has its own mechanism that sends the
completions via software CQE's directly to the relevant CQ.
This should be kept in fatal error too, so the driver should simulate
such CQE's with the specified error state in order to complete GSI QP
work requests.
Without the fix the next deadlock might appears:
schedule_timeout+0x274/0x350
wait_for_common+0xec/0x240
mcast_remove_one+0xd0/0x120 [ib_core]
ib_unregister_device+0x12c/0x230 [ib_core]
mlx5_ib_remove+0xc4/0x270 [mlx5_ib]
mlx5_detach_device+0x184/0x1a0 [mlx5_core]
mlx5_unload_one+0x308/0x340 [mlx5_core]
mlx5_pci_err_detected+0x74/0xe0 [mlx5_core]
Cc: <stable@vger.kernel.org> # 4.7 Fixes: 89ea94a7b6c4 ("IB/mlx5: Reset flow support for IB kernel ULPs") Signed-off-by: Erez Shitrit <erezsh@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To allow rereg_user_mr to modify the MR from read-only to writable without
using get_user_pages again, we needed to define the initial MR as writable.
However, this was originally done unconditionally, without taking into
account the writability of the underlying virtual memory.
As a result, any attempt to register a read-only MR over read-only
virtual memory failed.
To fix this, do not add the writable flag bit when the user virtual memory
is not writable (e.g. const memory).
However, when the underlying memory is NOT writable (and we therefore
do not define the initial MR as writable), the IB core adds a
"force writable" flag to its user-pages request. If this succeeds,
the reg_user_mr caller gets a writable copy of the original pages.
If the user-space caller then does a rereg_user_mr operation to enable
writability, this will succeed. This should not be allowed, since
the original virtual memory was not writable.
Cc: <stable@vger.kernel.org> Fixes: 9376932d0c26 ("IB/mlx4_ib: Add support for user MR re-registration") Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
A warm restart will fail to unload the driver, leaving link state
potentially flapping up to the point the BIOS resets the adapter.
Correct the issue by hooking the shutdown pci method,
which will bring port down.
Cc: <stable@vger.kernel.org> # 4.9.x Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Alex Estrin <alex.estrin@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There is a race condition in tpm_common_write function allowing
two threads on the same /dev/tpm<N>, or two different applications
on the same /dev/tpmrm<N> to overwrite each other commands/responses.
Fixed this by taking the priv->buffer_mutex early in the function.
Also converted the priv->data_pending from atomic to a regular size_t
type. There is no need for it to be atomic since it is only touched
under the protection of the priv->buffer_mutex.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com> Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If load context command returns with TPM2_RC_HANDLE or TPM2_RC_REFERENCE_H0
then we have use after free in line 114 and double free in 117.
Fixes: 4d57856a21ed2 ("tpm2: add session handle context saving and restoring to the space code") Cc: stable@vger.kernel.org Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com> Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> Signed-off--by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Immediately after the platform_device_unregister() the device will be
cleaned up. Accessing the freed pointer immediately after that will
crash the system.
Found this bug when kernel is built with CONFIG_PAGE_POISONING and testing
loading/unloading audio drivers in a loop on Qcom platforms.
Fix this by moving of_node_clear_flag() just before the unregister calls.
For strings, account for trailing \0 in property length field:
This is consistent with how dtc builds string properties.
Function __of_prop_dup() would misbehave on such properties as it duplicates
properties based on the property length field creating new string values
without trailing \0s.
Signed-off-by: Stefan M Schaeckeler <sschaeck@cisco.com> Reviewed-by: Frank Rowand <frank.rowand@sony.com> Tested-by: Frank Rowand <frank.rowand@sony.com> Cc: <stable@vger.kernel.org> Signed-off-by: Rob Herring <robh@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There is a problem with the sd-uhs mode when doing a soft reboot.
Switching back from 1.8v to 3.3v messes with the card, which no longer
respond (timeout errors). According to the specification, we should
perform a card reset (power cycling the card) but this is something we
cannot control on this design.
Then the only solution to restore the communication with the card is an
"unplug-plug" which is not acceptable
Until we find a solution, if any, disable the sd-uhs modes on this design.
For the people using uhs at the moment, there will a performance drop as
a result.
When rewriting swapper using nG mappings, we must performance cache
maintenance around each page table access in order to avoid coherency
problems with the host's cacheable alias under KVM. To ensure correct
ordering of the maintenance with respect to Device memory accesses made
with the Stage-1 MMU disabled, DMBs need to be added between the
maintenance and the corresponding memory access.
This patch adds a missing DMB between writing a new page table entry and
performing a clean+invalidate on the same line.
Fixes: f992b4dfd58b ("arm64: kpti: Add ->enable callback to remap swapper using nG mappings") Cc: <stable@vger.kernel.org> # 4.16.x- Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Commit 17c2895 ("arm64: Abstract syscallno manipulation") abstracts
out the pt_regs.syscallno value for a syscall cancelled by a tracer
as NO_SYSCALL, and provides helpers to set and check for this
condition. However, the way this was implemented has the
unintended side-effect of disabling part of the syscall restart
logic.
This comes about because the second in_syscall() check in
do_signal() re-evaluates the "in a syscall" condition based on the
updated pt_regs instead of the original pt_regs. forget_syscall()
is explicitly called prior to the second check in order to prevent
restart logic in the ret_to_user path being spuriously triggered,
which means that the second in_syscall() check always yields false.
This triggers a failure in
tools/testing/selftests/seccomp/seccomp_bpf.c, when using ptrace to
suppress a signal that interrups a nanosleep() syscall.
Misbehaviour of this type is only expected in the case where a
tracer suppresses a signal and the target process is either being
single-stepped or the interrupted syscall attempts to restart via
-ERESTARTBLOCK.
This patch restores the old behaviour by performing the
in_syscall() check only once at the start of the function.
Fixes: 17c289586009 ("arm64: Abstract syscallno manipulation") Signed-off-by: Dave Martin <Dave.Martin@arm.com> Reported-by: Sumit Semwal <sumit.semwal@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Cc: <stable@vger.kernel.org> # 4.14.x- Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The Denali NAND x-clock should be supplied by nand_x_clk, not by
nand_clk. Fix this, otherwise the Denali driver gets incorrect
clock frequency information and incorrectly configures the NAND
timing.
NUMREGBYTES (which is used as the size for gdb_regs[]) is incorrectly
based on DBG_MAX_REG_NUM instead of GDB_MAX_REGS. DBG_MAX_REG_NUM
is the number of total registers, while GDB_MAX_REGS is the number
of 'unsigned longs' it takes to serialize those registers. Since
FP registers require 3 'unsigned longs' each, DBG_MAX_REG_NUM is
smaller than GDB_MAX_REGS.
This causes GDB 8.0 give the following error on connect:
"Truncated register 19 in remote 'g' packet"
This also causes the register serialization/deserialization logic
to overflow gdb_regs[], overwriting whatever follows.
Fixes: 834b2964b7ab ("kgdb,arm: fix register dump") Cc: <stable@vger.kernel.org> # 2.6.37+ Signed-off-by: David Rivshin <drivshin@allworx.com> Acked-by: Rabin Vincent <rabin@rab.in> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently we see a kernel-oops reported on Power-9 while attaching a
context to an AFU, with radix-mode and sysfs attr 'prefault_mode' set
to anything other than 'none'. The backtrace of the oops is of this
form:
Unable to handle kernel paging request for data at address 0x00000080
Faulting instruction address: 0xc00800000bcf3b20
cpu 0x1: Vector: 300 (Data Access) at [c00000037f003800]
pc: c00800000bcf3b20: cxl_load_segment+0x178/0x290 [cxl]
lr: c00800000bcf39f0: cxl_load_segment+0x48/0x290 [cxl]
sp: c00000037f003a80
msr: 9000000000009033
dar: 80
dsisr: 40000000
current = 0xc00000037f280000
paca = 0xc0000003ffffe600 softe: 3 irq_happened: 0x01
pid = 3529, comm = afp_no_int
<snip>
cxl_prefault+0xfc/0x248 [cxl]
process_element_entry_psl9+0xd8/0x1a0 [cxl]
cxl_attach_dedicated_process_psl9+0x44/0x130 [cxl]
native_attach_process+0xc0/0x130 [cxl]
afu_ioctl+0x3f4/0x5e0 [cxl]
do_vfs_ioctl+0xdc/0x890
ksys_ioctl+0x68/0xf0
sys_ioctl+0x40/0xa0
system_call+0x58/0x6c
The issue is caused as on Power-8 the AFU attr 'prefault_mode' was
used to improve initial storage fault performance by prefaulting
process segments. However on Power-9 with radix mode we don't have
Storage-Segments that we can prefault. Also prefaulting process Pages
will be too costly and fine-grained.
Hence, since the prefaulting mechanism doesn't makes sense of
radix-mode, this patch updates prefault_mode_store() to not allow any
other value apart from CXL_PREFAULT_NONE when radix mode is enabled.
Unregister fadump on kexec down path otherwise the fadump registration
in new kexec-ed kernel complains that fadump is already registered.
This makes new kernel to continue using fadump registered by previous
kernel which may lead to invalid vmcore generation. Hence this patch
fixes this issue by un-registering fadump in fadump_cleanup() which is
called during kexec path so that new kernel can register fadump with
new valid values.
Fixes: b500afff11f6 ("fadump: Invalidate registration and release reserved memory for general use.") Cc: stable@vger.kernel.org # v3.4+ Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The commit 78eaa10f027c ("cpuidle: powernv/pseries: Auto-promotion of
snooze to deeper idle state") introduced a timeout for the snooze idle
state so that it could be eventually be promoted to a deeper idle
state. The snooze timeout value is static and set to the target
residency of the next idle state, which would train the cpuidle
governor to pick the next idle state eventually.
The unfortunate side-effect of this is that if the next idle state(s)
is disabled, the CPU will forever remain in snooze, despite the fact
that the system is completely idle, and other deeper idle states are
available.
This patch fixes the issue by dynamically setting the snooze timeout
to the target residency of the next enabled state on the device.
Before Patch:
POWER8 : Only nap disabled.
$ cpupower monitor sleep 30
sleep took 30.01297 seconds and exited with status 0
|Idle_Stats
PKG |CORE|CPU | snoo | Nap | Fast
0| 8| 0| 96.41| 0.00| 0.00
0| 8| 1| 96.43| 0.00| 0.00
0| 8| 2| 96.47| 0.00| 0.00
0| 8| 3| 96.35| 0.00| 0.00
0| 8| 4| 96.37| 0.00| 0.00
0| 8| 5| 96.37| 0.00| 0.00
0| 8| 6| 96.47| 0.00| 0.00
0| 8| 7| 96.47| 0.00| 0.00
Init all present cpus for deep states instead of "all possible" cpus.
Init fails if a possible cpu is guarded. Resulting in making only
non-deep states available for cpuidle/hotplug.
Stewart says, this means that for single threaded workloads, if you
guard out a CPU core you'll not get WoF (Workload Optimised
Frequency), which means that performance goes down when you wouldn't
expect it to.
Fixes: 77b54e9f213f ("powernv/powerpc: Add winkle support for offline cpus") Cc: stable@vger.kernel.org # v3.19+ Signed-off-by: Akshay Adiga <akshay.adiga@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
NX can set the 3rd bit in CR register for XER[SO] (Summary overflow)
which is not related to paste request. The current paste function
returns failure for a successful request when this bit is set. So mask
this bit and check the proper return status.
When IODA2 creates a PE, it creates an IOMMU table with it_ops::free
set to pnv_ioda2_table_free() which calls pnv_pci_ioda2_table_free_pages().
Since iommu_tce_table_put() calls it_ops::free when the last reference
to the table is released, explicit call to pnv_pci_ioda2_table_free_pages()
is not needed so let's remove it.
This should fix double free in the case of PCI hotuplug as
pnv_pci_ioda2_table_free_pages() does not reset neither
iommu_table::it_base nor ::it_size.
This was not exposed by SRIOV as it uses different code path via
pnv_pcibios_sriov_disable().
IODA1 does not inialize it_ops::free so it does not have this issue.
Back when we first introduced the DAWR, in commit 4ae7ebe9522a
("powerpc: Change hardware breakpoint to allow longer ranges"), we
screwed up the constraint making it a 1024 byte boundary rather than a
512. This makes the check overly permissive. Fortunately GDB is the
only real user and it always did they right thing, so we never
noticed.
This fixes the constraint to 512 bytes.
Fixes: 4ae7ebe9522a ("powerpc: Change hardware breakpoint to allow longer ranges") Cc: stable@vger.kernel.org # v3.9+ Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently memory is allocated for core-imc based on cpu_present_mask,
which has bit 'cpu' set iff cpu is populated. We use (cpu number / threads
per core) as the array index to access the memory.
Under some circumstances firmware marks a CPU as GUARDed CPU and boot the
system, until cleared of errors, these CPU's are unavailable for all
subsequent boots. GUARDed CPUs are possible but not present from linux
view, so it blows a hole when we assume the max length of our allocation
is driven by our max present cpus, where as one of the cpus might be online
and be beyond the max present cpus, due to the hole.
So (cpu number / threads per core) value bounds the array index and leads
to memory overflow.
Call trace observed during a guard test:
Faulting instruction address: 0xc000000000149f1c
cpu 0x69: Vector: 380 (Data Access Out of Range) at [c000003fea303420]
pc:c000000000149f1c: prefetch_freepointer+0x14/0x30
lr:c00000000014e0f8: __kmalloc+0x1a8/0x1ac
sp:c000003fea3036a0
msr:9000000000009033
dar:c9c54b2c91dbf6b7
current = 0xc000003fea2c0000
paca = 0xc00000000fddd880 softe: 3 irq_happened: 0x01
pid = 1, comm = swapper/104
Linux version 4.16.7-openpower1 (smc@smc-desktop) (gcc version 6.4.0
(Buildroot 2018.02.1-00006-ga8d1126)) #2 SMP Fri May 4 16:44:54 PDT 2018
enter ? for help
call trace:
__kmalloc+0x1a8/0x1ac
(unreliable)
init_imc_pmu+0x7f4/0xbf0
opal_imc_counters_probe+0x3fc/0x43c
platform_drv_probe+0x48/0x80
driver_probe_device+0x22c/0x308
__driver_attach+0xa0/0xd8
bus_for_each_dev+0x88/0xb4
driver_attach+0x2c/0x40
bus_add_driver+0x1e8/0x228
driver_register+0xd0/0x114
__platform_driver_register+0x50/0x64
opal_imc_driver_init+0x24/0x38
do_one_initcall+0x150/0x15c
kernel_init_freeable+0x250/0x254
kernel_init+0x1c/0x150
ret_from_kernel_thread+0x5c/0xc8
Allocating memory for core-imc based on cpu_possible_mask, which has
bit 'cpu' set iff cpu is populatable, will fix this issue.
In commit e2a800beaca1 ("powerpc/hw_brk: Fix off by one error when
validating DAWR region end") we fixed setting the DAWR end point to
its max value via PPC_PTRACE_SETHWDEBUG. Unfortunately we broke
PTRACE_SET_DEBUGREG when setting a 512 byte aligned breakpoint.
PTRACE_SET_DEBUGREG currently sets the length of the breakpoint to
zero (memset() in hw_breakpoint_init()). This worked with
arch_validate_hwbkpt_settings() before the above patch was applied but
is now broken if the breakpoint is 512byte aligned.
This sets the length of the breakpoint to 8 bytes when using
PTRACE_SET_DEBUGREG.
Fixes: e2a800beaca1 ("powerpc/hw_brk: Fix off by one error when validating DAWR region end") Cc: stable@vger.kernel.org # v3.11+ Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently we do not have an isync, or any other context synchronizing
instruction prior to the slbie/slbmte in _switch() that updates the
SLB entry for the kernel stack.
However that is not correct as outlined in the ISA.
From Power ISA Version 3.0B, Book III, Chapter 11, page 1133:
"Changing the contents of ... the contents of SLB entries ... can
have the side effect of altering the context in which data
addresses and instruction addresses are interpreted, and in which
instructions are executed and data accesses are performed.
...
These side effects need not occur in program order, and therefore
may require explicit synchronization by software.
...
The synchronizing instruction before the context-altering
instruction ensures that all instructions up to and including that
synchronizing instruction are fetched and executed in the context
that existed before the alteration."
And page 1136:
"For data accesses, the context synchronizing instruction before the
slbie, slbieg, slbia, slbmte, tlbie, or tlbiel instruction ensures
that all preceding instructions that access data storage have
completed to a point at which they have reported all exceptions
they will cause."
We're not aware of any bugs caused by this, but it should be fixed
regardless.
Add the missing isync when updating kernel stack SLB entry.
Cc: stable@vger.kernel.org Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
[mpe: Flesh out change log with more ISA text & explanation] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
syzbot is reporting NULL pointer dereference at fuse_ctl_remove_conn() [1].
Since fc->ctl_ndents is incremented by fuse_ctl_add_conn() when new_inode()
failed, fuse_ctl_remove_conn() reaches an inode-less dentry and tries to
clear d_inode(dentry)->i_private field.
Fix by only adding the dentry to the array after being fully set up.
When tearing down the control directory, do d_invalidate() on it to get rid
of any mounts that might have been added.
syzbot is reporting use-after-free at fuse_kill_sb_blk() [1].
Since sb->s_fs_info field is not cleared after fc was released by
fuse_conn_put() when initialization failed, fuse_kill_sb_blk() finds
already released fc and tries to hold the lock. Fix this by clearing
sb->s_fs_info field after calling fuse_conn_put().
Fuse has an "atomic_o_trunc" mode, where userspace filesystem uses the
O_TRUNC flag in the OPEN request to truncate the file atomically with the
open.
In this mode there's no need to send a SETATTR request to userspace after
the open, so fuse_do_setattr() checks this mode and returns. But this
misses the important step of truncating the pagecache.
Add the missing parts of truncation to the ATTR_OPEN branch.
If a connection gets aborted while congested, FUSE can leave
nr_wb_congested[] stuck until reboot causing wait_iff_congested() to
wait spuriously which can lead to severe performance degradation.
The leak is caused by gating congestion state clearing with
fc->connected test in request_end(). This was added way back in 2009
by 26c3679101db ("fuse: destroy bdi on umount"). While the commit
description doesn't explain why the test was added, it most likely was
to avoid dereferencing bdi after it got destroyed.
Since then, bdi lifetime rules have changed many times and now we're
always guaranteed to have access to the bdi while the superblock is
alive (fc->sb).
Drop fc->connected conditional to avoid leaking congestion states.
Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Joshua Miller <joshmiller@fb.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: stable@vger.kernel.org # v2.6.29+ Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
I noticed that there is a possibility that printk_safe_log_store() causes
kernel oops because "args" parameter is passed to vsnprintf() again when
atomic_cmpxchg() detected that we raced. Fix this by using va_copy().
Link: http://lkml.kernel.org/r/201805112002.GIF21216.OFVHFOMLJtQFSO@I-love.SAKURA.ne.jp Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: dvyukov@google.com Cc: syzkaller@googlegroups.com Cc: fengguang.wu@intel.com Cc: linux-kernel@vger.kernel.org Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Fixes: 42a0bb3f71383b45 ("printk/nmi: generic solution for safe printk in NMI") Cc: 4.7+ <stable@vger.kernel.org> # v4.7+ Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
AOSP use userspace firmware loader to load firmwares, which will
return -EAGAIN in case qca/rampatch_00440302.bin is not found.
Since there is no rampatch for dragonboard820c QCA controller
revision, just make it work as is.
There was one place where the timeout value for an operation was
not being set, if a capabilities request was done from idle. Move
the timeout value setting to before where that change might be
requested.
IMHO the cause here is the invisible returns in the macros. Maybe
that's a job for later, though.
The function __builtin_expect returns long type (see the gcc
documentation), and so do macros likely and unlikely. Unfortunatelly, when
CONFIG_PROFILE_ANNOTATED_BRANCHES is selected, the macros likely and
unlikely expand to __branch_check__ and __branch_check__ truncates the
long type to int. This unintended truncation may cause bugs in various
kernel code (we found a bug in dm-writecache because of it), so it's
better to fix __branch_check__ to return long.
ftrace_graph_caller was never run after calling ftrace_trace_function,
breaking the function graph tracer. Fix this, bringing it in line with the
x86 implementation.
While we're at it, also streamline the control flow of _mcount a bit to
reduce the number of branches.
This issue was reported before:
https://www.linux-mips.org/archives/linux-mips/2014-11/msg00295.html
The trigger code is picky in how it can be disabled as there may be
dependencies between different events and synthetic events. Change the order
on how triggers are reset.
1) Reset triggers of all synthetic events first
2) Remove triggers with actions attached to them
3) Remove all other triggers
If this order isn't followed, then some triggers will not be reset, and an
error may happen because a trigger is busy.
"%pCr" formats the current rate of a clock, and calls clk_get_rate().
The latter obtains a mutex, hence it must not be called from atomic
context.
Remove support for this rarely-used format, as vsprintf() (and e.g.
printk()) must be callable from any context.
Any remaining out-of-tree users will start seeing the clock's name
printed instead of its rate.
Reported-by: Jia-Ju Bai <baijiaju1990@gmail.com> Fixes: 900cca2944254edd ("lib/vsprintf: add %pC{,n,r} format specifiers for clocks") Link: http://lkml.kernel.org/r/1527845302-12159-5-git-send-email-geert+renesas@glider.be
To: Jia-Ju Bai <baijiaju1990@gmail.com>
To: Jonathan Corbet <corbet@lwn.net>
To: Michael Turquette <mturquette@baylibre.com>
To: Stephen Boyd <sboyd@kernel.org>
To: Zhang Rui <rui.zhang@intel.com>
To: Eduardo Valentin <edubezval@gmail.com>
To: Eric Anholt <eric@anholt.net>
To: Stefan Wahren <stefan.wahren@i2se.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: linux-doc@vger.kernel.org Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: linux-serial@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-renesas-soc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: stable@vger.kernel.org # 4.1+ Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Printk format "%pCr" will be removed soon, as clk_get_rate() must not be
called in atomic context.
Replace it by open-coding the operation. This is safe here, as the code
runs in task context.
Link: http://lkml.kernel.org/r/1527845302-12159-2-git-send-email-geert+renesas@glider.be
To: Jia-Ju Bai <baijiaju1990@gmail.com>
To: Jonathan Corbet <corbet@lwn.net>
To: Michael Turquette <mturquette@baylibre.com>
To: Stephen Boyd <sboyd@kernel.org>
To: Zhang Rui <rui.zhang@intel.com>
To: Eduardo Valentin <edubezval@gmail.com>
To: Eric Anholt <eric@anholt.net>
To: Stefan Wahren <stefan.wahren@i2se.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: linux-doc@vger.kernel.org Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: linux-serial@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-renesas-soc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: stable@vger.kernel.org # 4.5+ Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be> Acked-by: Stephen Boyd <sboyd@kernel.org> Signed-off-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Printk format "%pCr" will be removed soon, as clk_get_rate() must not be
called in atomic context.
Replace it by printing the variable that already holds the clock rate.
Note that calling clk_get_rate() is safe here, as the code runs in task
context.
Link: http://lkml.kernel.org/r/1527845302-12159-3-git-send-email-geert+renesas@glider.be
To: Jia-Ju Bai <baijiaju1990@gmail.com>
To: Jonathan Corbet <corbet@lwn.net>
To: Michael Turquette <mturquette@baylibre.com>
To: Stephen Boyd <sboyd@kernel.org>
To: Zhang Rui <rui.zhang@intel.com>
To: Eduardo Valentin <edubezval@gmail.com>
To: Eric Anholt <eric@anholt.net>
To: Stefan Wahren <stefan.wahren@i2se.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: linux-doc@vger.kernel.org Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: linux-serial@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-renesas-soc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # 4.12+ Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be> Acked-by: Stefan Wahren <stefan.wahren@i2se.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
According to "EP93xx User’s Guide", I2STXLinCtrlData and I2SRXLinCtrlData
registers actually have different format. The only currently used bit
(Left_Right_Justify) has different position. Fix this and simplify the
whole setup taking into account the fact that both registers have zero
default value.
The practical effect of the above is repaired SND_SOC_DAIFMT_RIGHT_J
support (currently unused).
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@gmail.com> Signed-off-by: Mark Brown <broonie@kernel.org> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The bit responsible for LRCLK polarity is i2s_tlrs (0), not i2s_trel (2)
(refer to "EP93xx User's Guide").
Previously card drivers which specified SND_SOC_DAIFMT_NB_IF actually got
SND_SOC_DAIFMT_NB_NF, an adaptation is necessary to retain the old
behavior.
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@gmail.com> Signed-off-by: Mark Brown <broonie@kernel.org> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add the use_single_rw flag to regmap config since the
device does not support bulk transactions over i2c.
Signed-off-by: Paul Handrigan <Paul.Handrigan@cirrus.com> Signed-off-by: Mark Brown <broonie@kernel.org> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Some low-speed and full-speed devices (for example, bluetooth)
do not have time to initialize. For them, ETIMEDOUT is a valid error.
We need to give them another try. Otherwise, they will
never be initialized correctly and in dmesg will be messages
"Bluetooth: hci0 command 0x1002 tx timeout" or similars.
Fixes: 264904ccc33c ("usb: retry reset if a device times out") Cc: stable <stable@vger.kernel.org> Signed-off-by: Maxim Moseychuk <franchesko.salias.hudro.pedros@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit fixes a rare but possible case when the clk rate is updated
without update of the regulator voltage.
At boot up, CPUfreq checks if the system is running at the right freq. This
is a sanity check in case a bootloader set clk rate that is outside of freq
table present with cpufreq core. In such cases system can be unstable so
better to change it to a freq that is preset in freq-table.
The CPUfreq takes next freq that is >= policy->cur and this is our
target_freq that needs to be set now.
dev_pm_opp_set_rate(dev, target_freq) checks the target_freq and the
old_freq (a current rate). If these are equal it returns early. If not,
it searches for OPP (old_opp) that fits best to old_freq (not listed in
the table) and updates old_freq (!).
Here, we can end up with old_freq = old_opp.rate = target_freq, which
is not handled in _generic_set_opp_regulator(). It's supposed to update
voltage only when freq > old_freq || freq > old_freq.
if (freq > old_freq) {
ret = _set_opp_voltage(dev, reg, new_supply);
[...]
if (freq < old_freq) {
ret = _set_opp_voltage(dev, reg, new_supply);
if (ret)
It results in, no voltage update while clk rate is updated.
If a device link is added via device_link_add() by the driver of the
link's consumer device, the supplier's runtime PM usage counter is
going to be dropped by the pm_runtime_put_suppliers() call in
driver_probe_device(). However, in that case it is not incremented
unless the supplier driver is already present and the link is not
stateless. That leads to a runtime PM usage counter imbalance for
the supplier device in a few cases.
To prevent that from happening, bump up the supplier runtime
PM usage counter in device_link_add() for all links with the
DL_FLAG_PM_RUNTIME flag set that are added at the consumer probe
time. Use pm_runtime_get_noresume() for that as the callers of
device_link_add() who want the supplier to be resumed by it are
expected to pass DL_FLAG_RPM_ACTIVE in flags to it anyway, but
additionally resume the supplier if the link is added during
consumer driver probe to retain the existing behavior for the
callers depending on it.
Fixes: 21d5c57b3726 (PM / runtime: Use device links) Reported-by: Ulf Hansson <ulf.hansson@linaro.org> Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org> Tested-by: Marek Szyprowski <m.szyprowski@samsung.com> Cc: 4.10+ <stable@vger.kernel.org> # 4.10+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In case the PM domain fails to be powered on in genpd_dev_pm_attach(), it
returns -EPROBE_DEFER, but keeping the device attached to its PM domain.
This leads to problems when the next attempt to attach is re-tried. More
precisely, in that situation an -EEXIST error code is returned, because the
device already has its PM domain pointer assigned, from the first attempt.
Now, because of the sloppy error handling by the existing callers of
dev_pm_domain_attach(), probing is allowed to continue when -EEXIST is
returned. However, in such case there are no guarantees that the PM domain
is powered on by genpd, which may lead to hangs when buses/drivers tried to
access their devices.
Let's fix this behaviour, simply by detaching the device when powering on
fails in genpd_dev_pm_attach().
Cc: v4.11+ <stable@vger.kernel.org> # v4.11+ Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
While working on changing this code to use force_sig_fault I
discovered that do_unaliged_user is sets si_signo to SIGBUS and passes
SIGSEGV to force_sig_info. Which is just b0rked.
The code is reporting a SIGBUS error so replace the SIGSEGV with SIGBUS.
Cc: Chris Zankel <chris@zankel.net> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: linux-xtensa@linux-xtensa.org Cc: stable@vger.kernel.org Acked-by: Max Filippov <jcmvbkbc@gmail.com> Fixes: 5a0015d62668 ("[PATCH] xtensa: Architecture support for Tensilica Xtensa Part 3") Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Commit 40f70c03e33a ("serial: sh-sci: add locking to console write
function to avoid SMP lockup") copied the strategy to avoid locking
problems in conjuncture with the console from the UART8250
driver. Instead using directly spin_{try}lock_irqsave(),
local_irq_save() followed by spin_{try}lock() was used. While this is
correct on mainline, for -rt it is a problem. spin_{try}lock() will
check if it is running in a valid context. Since the local_irq_save()
has already been executed, the context has changed and
spin_{try}lock() will complain. The reason why spin_{try}lock()
complains is that on -rt the spin locks are turned into mutexes and
therefore can sleep. Sleeping with interrupts disabled is not valid.
If 020/030 support is enabled, get_io_area() leaves an IO_SIZE gap
between mappings which is added to the vm_struct representing the
mapping. __ioremap() uses the actual requested size (after alignment),
while __iounmap() is passed the size from the vm_struct.
On 020/030, early termination descriptors are used to set up mappings of
extent 'size', which are validated on unmapping. The unmapped gap of
size IO_SIZE defeats the sanity check of the pmd tables, causing
__iounmap() to loop forever on 030.
On 040/060, unmapping of page table entries does not check for a valid
mapping, so the umapping loop always completes there.
Adjust size to be unmapped by the gap that had been added in the
vm_struct prior.
This fixes the hang in atari_platform_init() reported a long time ago,
and a similar one reported by Finn recently (addressed by removing
ioremap() use from the SWIM driver.
Tested on my Falcon in 030 mode - untested but should work the same on
040/060 (the extra page tables cleared there would never have been set
up anyway).
Signed-off-by: Michael Schmitz <schmitzmic@gmail.com>
[geert: Minor commit description improvements]
[geert: This was fixed in 2.4.23, but not in 2.5.x] Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
fpu__drop() has an explicit fwait which under some conditions can trigger a
fixable FPU exception while in kernel. Thus, we should attempt to fixup the
exception first, and only call notify_die() if the fixup failed just like
in do_general_protection(). The original call sequence incorrectly triggers
KDB entry on debug kernels under particular FPU-intensive workloads.
Andy noted, that this makes the whole conditional irq enable thing even
more inconsistent, but fixing that it outside the scope of this.
Signed-off-by: Siarhei Liakh <siarhei.liakh@concurrent-rt.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Borislav Petkov" <bpetkov@suse.de> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/DM5PR11MB201156F1CAB2592B07C79A03B17D0@DM5PR11MB2011.namprd11.prod.outlook.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
mce_no_way_out() does a quick check during #MC to see whether some of
the MCEs logged would require the kernel to panic immediately. And it
passes a struct mce where MCi_STATUS gets written.
However, after having saved a valid status value, the next iteration
of the loop which goes over the MCA banks on the CPU, overwrites the
valid status value because we're using struct mce as storage instead of
a temporary variable.
Which leads to MCE records with an empty status value:
mce: [Hardware Error]: CPU 0: Machine Check Exception: 6 Bank 0: 0000000000000000
mce: [Hardware Error]: RIP 10:<ffffffffbd42fbd7> {trigger_mce+0x7/0x10}
In order to prevent the loss of the status register value, return
immediately when severity is a panic one so that we can panic
immediately with the first fatal MCE logged. This is also the intention
of this function and not to noodle over the banks while a fatal MCE is
already logged.
Tony: read the rest of the MCA bank to populate the struct mce fully.
Suggested-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Link: https://lkml.kernel.org/r/20180622095428.626-8-bp@alien8.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Some injection testing resulted in the following console log:
mce: [Hardware Error]: CPU 22: Machine Check Exception: f Bank 1: bd80000000100134
mce: [Hardware Error]: RIP 10:<ffffffffc05292dd> {pmem_do_bvec+0x11d/0x330 [nd_pmem]}
mce: [Hardware Error]: TSC c51a63035d52 ADDR 3234bc4000 MISC 88
mce: [Hardware Error]: PROCESSOR 0:50654 TIME 1526502199 SOCKET 0 APIC 38 microcode 2000043
mce: [Hardware Error]: Run the above through 'mcelog --ascii'
Kernel panic - not syncing: Machine check from unknown source
This confused everybody because the first line quite clearly shows
that we found a logged error in "Bank 1", while the last line says
"unknown source".
The problem is that the Linux code doesn't do the right thing
for a local machine check that results in a fatal error.
It turns out that we know very early in the handler whether the
machine check is fatal. The call to mce_no_way_out() has checked
all the banks for the CPU that took the local machine check. If
it says we must crash, we can do so right away with the right
messages.
We do scan all the banks again. This means that we might initially
not see a problem, but during the second scan find something fatal.
If this happens we print a slightly different message (so I can
see if it actually every happens).
[ bp: Remove unneeded severity assignment. ]
Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: stable@vger.kernel.org # 4.2 Link: http://lkml.kernel.org/r/52e049a497e86fd0b71c529651def8871c804df0.1527283897.git.tony.luck@intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently we just check the "CAPID0" register to see whether the CPU
can recover from machine checks.
But there are also some special SKUs which do not have all advanced
RAS features, but do enable machine check recovery for use with NVDIMMs.
Add a check for any of bits {8:5} in the "CAPID5" register (each
reports some NVDIMM mode available, if any of them are set, then
the system supports memory machine check recovery).
Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: stable@vger.kernel.org # 4.9 Cc: Dan Williams <dan.j.williams@intel.com> Cc: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/03cbed6e99ddafb51c2eadf9a3b7c8d7a0cc204e.1527283897.git.tony.luck@intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Since we added support to add recovery from some errors inside the kernel in:
commit b2f9d678e28c ("x86/mce: Check for faults tagged in EXTABLE_CLASS_FAULT exception table entries")
we have done a less than stellar job at reporting the cause of recoverable
machine checks that occur in other parts of the kernel. The user just gets
the unhelpful message:
doubly unhelpful when they check the manual for the reported IA32_MSR_STATUS.MCACOD
and see that it is listed as one of the standard recoverable values.
Add an extra rule to the MCE severity table to catch this case and report it
as:
mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel
Fixes: b2f9d678e28c ("x86/mce: Check for faults tagged in EXTABLE_CLASS_FAULT exception table entries") Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: stable@vger.kernel.org # 4.6+ Cc: Dan Williams <dan.j.williams@intel.com> Cc: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/4cc7c465150a9a48b8b9f45d0b840278e77eb9b5.1527283897.git.tony.luck@intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Mark Rutland noticed that GCC optimization passes have the potential to elide
necessary invocations of the array_index_mask_nospec() instruction sequence,
so mark the asm() volatile.
Mark explains:
"The volatile will inhibit *some* cases where the compiler could lift the
array_index_nospec() call out of a branch, e.g. where there are multiple
invocations of array_index_nospec() with the same arguments:
... since the compiler can determine that the two invocations yield the same
result, and reuse the first result (likely the same register as idx was in
originally) for the second branch, effectively re-writing the above as:
In __alloc_pages_slowpath() we reset zonelist and preferred_zoneref for
allocations that can ignore memory policies. The zonelist is obtained
from current CPU's node. This is a problem for __GFP_THISNODE
allocations that want to allocate on a different node, e.g. because the
allocating thread has been migrated to a different CPU.
This has been observed to break SLAB in our 4.4-based kernel, because
there it relies on __GFP_THISNODE working as intended. If a slab page
is put on wrong node's list, then further list manipulations may corrupt
the list because page_to_nid() is used to determine which node's
list_lock should be locked and thus we may take a wrong lock and race.
Current SLAB implementation seems to be immune by luck thanks to commit 511e3a058812 ("mm/slab: make cache_grow() handle the page allocated on
arbitrary node") but there may be others assuming that __GFP_THISNODE
works as promised.
We can fix it by simply removing the zonelist reset completely. There
is actually no reason to reset it, because memory policies and cpusets
don't affect the zonelist choice in the first place. This was different
when commit 183f6371aac2 ("mm: ignore mempolicies when using
ALLOC_NO_WATERMARK") introduced the code, as mempolicies provided their
own restricted zonelists.
We might consider this for 4.17 although I don't know if there's
anything currently broken.
SLAB is currently not affected, but in kernels older than 4.7 that don't
yet have 511e3a058812 ("mm/slab: make cache_grow() handle the page
allocated on arbitrary node") it is. That's at least 4.4 LTS. Older
ones I'll have to check.
So stable backports should be more important, but will have to be
reviewed carefully, as the code went through many changes. BTW I think
that also the ac->preferred_zoneref reset is currently useless if we
don't also reset ac->nodemask from a mempolicy to NULL first (which we
probably should for the OOM victims etc?), but I would leave that for a
separate patch.
Link: http://lkml.kernel.org/r/20180525130853.13915-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Fixes: 183f6371aac2 ("mm: ignore mempolicies when using ALLOC_NO_WATERMARK") Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
WHen registering a new binfmt_misc handler, it is possible to overflow
the offset to get a negative value, which might crash the system, or
possibly leak kernel data.
Here is a crash log when 2500000000 was used as an offset:
Use kstrtoint instead of simple_strtoul. It will work as the code
already set the delimiter byte to '\0' and we only do it when the field
is not empty.
Tested with offsets -1, 2500000000, UINT_MAX and INT_MAX. Also tested
with examples documented at Documentation/admin-guide/binfmt-misc.rst
and other registrations from packages on Ubuntu.
Link: http://lkml.kernel.org/r/20180529135648.14254-1-cascardo@canonical.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
struct vhost_msg within struct vhost_msg_node is copied to userspace.
Unfortunately it turns out on 64 bit systems vhost_msg has padding after
type which gcc doesn't initialize, leaking 4 uninitialized bytes to
userspace.
This padding also unfortunately means 32 bit users of this interface are
broken on a 64 bit kernel which will need to be fixed separately.
Fixes: CVE-2018-1118 Cc: stable@vger.kernel.org Reported-by: Kevin Easton <kevin@guarana.org> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reported-by: syzbot+87cfa083e727a224754b@syzkaller.appspotmail.com Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The HID descriptor for the 2nd-gen Intuos Pro large (PTH-860) contains
a typo which defines an incorrect logical maximum Y value. This causes
a small portion of the bottom of the tablet to become unusable (both
because the area is below the "bottom" of the tablet and because
'wacom_wac_event' ignores out-of-range values). It also results in a
skewed aspect ratio.
To fix this, we add a quirk to 'wacom_usage_mapping' which overwrites
the data with the correct value.
Current ISH driver only registers suspend/resume PM callbacks which don't
support hibernation (suspend to disk). Basically after hiberation, the ISH
can't resume properly and user may not see sensor events (for example: screen
rotation may not work).
User will not see a crash or panic or anything except the following message
in log:
hid-sensor-hub 001F:8086:22D8.0001: timeout waiting for response from ISHTP device
So this patch adds support for S4/hiberbation to ISH by using the
SIMPLE_DEV_PM_OPS() MACRO instead of struct dev_pm_ops directly. The suspend
and resume functions will now be used for both suspend to RAM and hibernation.
If power management is disabled, SIMPLE_DEV_PM_OPS will do nothing, the suspend
and resume related functions won't be used, so mark them as __maybe_unused to
clarify that this is the intended behavior, and remove #ifdefs for power
management.
As long as a symlink inode remains in-core, the destination (and
therefore size) will not be re-fetched from the server, as it cannot
change. The original implementation of the attribute cache assumed that
setting the expiry time in the past was sufficient to cause a re-fetch
of all attributes on the next getattr. That does not work in this case.
The bug manifested itself as follows. When the command sequence
The page loading code trusts the data provided in the firmware images
a bit too much and may cause a buffer overflow or copy unknown data if
the block sizes don't match what we expect.
To prevent potential problems, harden the code by checking if the
sizes we are copying are what we expect.
Commit 184add2ca23c ("libata: Apply NOLPM quirk for SanDisk
SD7UB3Q*G1001 SSDs") disabled LPM for SanDisk SD7UB3Q*G1001 SSDs.
This has lead to several reports of users of that SSD where LPM
was working fine and who know have a significantly increased idle
power consumption on their laptops.
Likely there is another problem on the T450s from the original
reporter which gets exposed by the uncore reaching deeper sleep
states (higher PC-states) due to LPM being enabled. The problem as
reported, a hardfreeze about once a day, already did not sound like
it would be caused by LPM and the reports of the SSD working fine
confirm this. The original reporter is ok with dropping the quirk.
A X250 user has reported the same hard freeze problem and for him
the problem went away after unrelated updates, I suspect some GPU
driver stack changes fixed things.
TL;DR: The original reporters problem were triggered by LPM but not
an LPM issue, so drop the quirk for the SSD in question.
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1583207 Cc: stable@vger.kernel.org Cc: Richard W.M. Jones <rjones@redhat.com> Cc: Lorenzo Dalrio <lorenzo.dalrio@gmail.com> Reported-by: Lorenzo Dalrio <lorenzo.dalrio@gmail.com> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Richard W.M. Jones" <rjones@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
According to current code implementation, detecting the long
idle period is done by checking if the interval between two
adjacent utilization update handlers is long enough. Although
this mechanism can detect if the idle period is long enough
(no utilization hooks invoked during idle period), it might
not cover a corner case: if the task has occupied the CPU
for too long which causes no context switches during that
period, then no utilization handler will be launched until this
high prio task is scheduled out. As a result, the idle_periods
field might be calculated incorrectly because it regards the
100% load as 0% and makes the conservative governor who uses
this field confusing.
Change the detection to compare the idle_time with sampling_rate
directly.
Reported-by: Artem S. Tashkinov <t.artem@mailcity.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: All applicable <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If the policy limits are updated via cpufreq_update_policy() and
subsequently via sysfs, the limits stored in user_policy may be
set incorrectly.
For example, if both min and max are set via sysfs to the maximum
available frequency, user_policy.min and user_policy.max will also
be the maximum. If a policy notifier triggered by
cpufreq_update_policy() lowers both the min and the max at this
point, that change is not reflected by the user_policy limits, so
if the max is updated again via sysfs to the same lower value,
then user_policy.max will be lower than user_policy.min which
shouldn't happen. In particular, if one of the policy CPUs is
then taken offline and back online, cpufreq_set_policy() will
fail for it due to a failing limits check.
To prevent that from happening, initialize the min and max fields
of the new_policy object to the ones stored in user_policy that
were previously set via sysfs.
Signed-off-by: Kevin Wangtao <kevin.wangtao@hisilicon.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
[ rjw: Subject & changelog ] Cc: All applicable <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cgwb_release() punts the actual release to cgwb_release_workfn() on
system_wq. Depending on the number of cgroups or block devices, there
can be a lot of cgwb_release_workfn() in flight at the same time.
We're periodically seeing close to 256 kworkers getting stuck with the
following stack trace and overtime the entire system gets stuck.
1. A lot of cgwb_release_workfn() is queued at the same time and all
system_wq kworkers are assigned to execute them.
2. They all end up calling synchronize_rcu_expedited(). One of them
wins and tries to perform the expedited synchronization.
3. However, that invovles queueing rcu_exp_work to system_wq and
waiting for it. Because #1 is holding all available kworkers on
system_wq, rcu_exp_work can't be executed. cgwb_release_workfn()
is waiting for synchronize_rcu_expedited() which in turn is waiting
for cgwb_release_workfn() to free up some of the kworkers.
We shouldn't be scheduling hundreds of cgwb_release_workfn() at the
same time. There's nothing to be gained from that. This patch
updates cgwb release path to use a dedicated percpu workqueue with
@max_active of 1.
While this resolves the problem at hand, it might be a good idea to
isolate rcu_exp_work to its own workqueue too as it can be used from
various paths and is prone to this sort of indirect A-A deadlocks.
It is not allowed to reinit q->tag_set_list list entry while RCU grace
period has not completed yet, otherwise the following soft lockup in
blk_mq_sched_restart() happens:
1. There are several MQ queues with shared tags.
2. One queue is about to be freed and now task is in
blk_mq_del_queue_tag_set().
3. Other CPU is in blk_mq_sched_restart() and loops over all queues in
tag list in order to find hctx to restart.
Because linked list entry was modified in blk_mq_del_queue_tag_set()
without proper waiting for a grace period, blk_mq_sched_restart()
never ends, spining in list_for_each_entry_rcu_rr(), thus soft lockup.
Fix is simple: reinit list entry after an RCU grace period elapsed.
Fixes: Fixes: 705cda97ee3a ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list") Cc: stable@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-block@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com> Signed-off-by: Roman Pen <roman.penyaev@profitbricks.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When we stopped relying on the bdev everywhere I broke updating the
block device size on the fly, which ceph relies on. We can't just do
set_capacity, we also have to do bd_set_size so things like parted will
notice the device size change.
Fixes: 29eaadc ("nbd: stop using the bdev everywhere")
cc: stable@vger.kernel.org Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
I messed up changing the size of an NBD device while it was connected by
not actually updating the device or doing the uevent. Fix this by
updating everything if we're connected and we change the size.
cc: stable@vger.kernel.org Fixes: 639812a ("nbd: don't set the device size until we're connected") Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This fixes a use after free bug, we shouldn't be doing disk->queue right
after we do del_gendisk(disk). Save the queue and do the cleanup after
the del_gendisk.
projects / users / jedix / linux-maple.git / log