| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
On some systems that are vulnerable to Spectre v2, it is up to
software to flush the link stack (return address stack), in order to
protect against Spectre-RSB.
When exiting from a guest we do some house keeping and then
potentially exit to C code which is several stack frames deep in the
host kernel. We will then execute a series of returns without
preceeding calls, opening up the possiblity that the guest could have
poisoned the link stack, and direct speculative execution of the host
to a gadget of some sort.
To prevent this we add a flush of the link stack on exit from a guest.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
In commit ee13cb249fab ("powerpc/64s: Add support for software count
cache flush"), I added support for software to flush the count
cache (indirect branch cache) on context switch if firmware told us
that was the required mitigation for Spectre v2.
As part of that code we also added a software flush of the link
stack (return address stack), which protects against Spectre-RSB
between user processes.
That is all correct for CPUs that activate that mitigation, which is
currently Power9 Nimbus DD2.3.
What I got wrong is that on older CPUs, where firmware has disabled
the count cache, we also need to flush the link stack on context
switch.
To fix it we create a new feature bit which is not set by firmware,
which tells us we need to flush the link stack. We set that when
firmware tells us that either of the existing Spectre v2 mitigations
are enabled.
Then we adjust the patching code so that if we see that feature bit we
enable the link stack flush. If we're also told to flush the count
cache in software then we fall through and do that also.
On the older CPUs we don't need to do do the software count cache
flush, firmware has disabled it, so in that case we patch in an early
return after the link stack flush.
The naming of some of the functions is awkward after this patch,
because they're called "count cache" but they also do link stack. But
we'll fix that up in a later commit to ease backporting.
This is the fix for CVE-2019-18660.
Reported-by: Anthony Steinhauser <asteinhauser@google.com>
Fixes: ee13cb249fab ("powerpc/64s: Add support for software count cache flush")
Cc: stable@vger.kernel.org # v4.4+
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Like all other architectures such as x86 or arm64, include KASLR offset
in VMCOREINFO ELF notes to assist in debugging. After this, we can use
crash --kaslr option to parse vmcore generated from a kaslr kernel.
Note: The crash tool needs to support --kaslr too.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
When kaslr is enabled, the kernel offset is different for every boot.
This brings some difficult to debug the kernel. Dump out the kernel
offset when panic so that we can easily debug the kernel.
This code is derived from x86/arm64 which has similar functionality.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
One may want to disable kaslr when boot, so provide a cmdline parameter
'nokaslr' to support this.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
The original kernel still exists in the memory, clear it now.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
After we have the basic support of relocate the kernel in some
appropriate place, we can start to randomize the offset now.
Entropy is derived from the banner and timer, which will change every
build and boot. This not so much safe so additionally the bootloader may
pass entropy via the /chosen/kaslr-seed node in device tree.
We will use the first 512M of the low memory to randomize the kernel
image. The memory will be split in 64M zones. We will use the lower 8
bit of the entropy to decide the index of the 64M zone. Then we chose a
16K aligned offset inside the 64M zone to put the kernel in.
We also check if we will overlap with some areas like the dtb area, the
initrd area or the crashkernel area. If we cannot find a proper area,
kaslr will be disabled and boot from the original kernel.
Some pieces of code are derived from arch/x86/boot/compressed/kaslr.c or
arch/arm64/kernel/kaslr.c such as rotate_xor(). Credit goes to Kees and
Ard.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
This patch add support to boot kernel from places other than KERNELBASE.
Since CONFIG_RELOCATABLE has already supported, what we need to do is
map or copy kernel to a proper place and relocate. Freescale Book-E
parts expect lowmem to be mapped by fixed TLB entries(TLB1). The TLB1
entries are not suitable to map the kernel directly in a randomized
region, so we chose to copy the kernel to a proper place and restart to
relocate.
The offset of the kernel was not randomized yet(a fixed 64M is set). We
will randomize it in the next patch.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
[mpe: Use PTRRELOC() in early_init()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Add a new helper reloc_kernel_entry() to jump back to the start of the
new kernel. After we put the new kernel in a randomized place we can use
this new helper to enter the kernel and begin to relocate again.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Add a new helper create_kaslr_tlb_entry() to create a tlb entry by the
virtual and physical address. This is a preparation to support boot kernel
at a randomized address.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Now the kernel base is a fixed value - KERNELBASE. To support KASLR, we
need a variable to store the kernel base.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
These two variables are both defined in init_32.c and init_64.c. Move
them to init-common.c and make them __ro_after_init.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
M_IF_NEEDED is defined too many times. Move it to a common place and
rename it to MAS2_M_IF_NEEDED which is much readable.
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Diana Craciun <diana.craciun@nxp.com>
Tested-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Currently it is not possible to distinguish the case when fadump is
supported by firmware and disabled in kernel and completely unsupported
using the kernel sysfs interface. User can investigate the devicetree
but it is more reasonable to provide sysfs files in case we get some
fadumpv2 in the future.
With this patch sysfs files are available whenever fadump is supported
by firmware.
There is duplicate message about lack of support by firmware in
fadump_reserve_mem and setup_fadump. Remove the duplicate message in
setup_fadump.
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Reviewed-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191107164757.15140-1-msuchanek@suse.de
|
|
Since commit ed1cd6deb013 ("powerpc: Activate CONFIG_THREAD_INFO_IN_TASK")
current_is_64bit() is quivalent to !is_32bit_task().
Remove the redundant function.
Suggested-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190912194633.12045-1-msuchanek@suse.de
|
|
Currently when an EEH error is detected, the system log receives the
same (or almost the same) message twice:
EEH: PHB#0 failure detected, location: N/A
EEH: PHB#0 failure detected, location: N/A
or
EEH: eeh_dev_check_failure: Frozen PHB#0-PE#0 detected
EEH: Frozen PHB#0-PE#0 detected
This looks like a bug, but in fact the messages are from different
functions and mean slightly different things. So keep both but change
one of the messages slightly, so that it's clear they are different:
EEH: PHB#0 failure detected, location: N/A
EEH: Recovering PHB#0, location: N/A
or
EEH: eeh_dev_check_failure: Frozen PHB#0-PE#0 detected
EEH: Recovering PHB#0-PE#0
Signed-off-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/43817cb6e6631b0828b9a6e266f60d1f8ca8eb22.1571288375.git.sbobroff@linux.ibm.com
|
|
Changes the return variable to bool (as the return value) and
avoids doing a ternary operation before returning.
Signed-off-by: Leonardo Bras <leonardo@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190802133914.30413-1-leonardo@linux.ibm.com
|
|
The powerpc version of dma-mapping.h only contains a version of
get_arch_dma_ops that always return NULL. Replace it with the
asm-generic version that does the same.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190807150752.17894-1-hch@lst.de
|
|
When the machine crash handler is invoked, all interrupts are masked
but interrupts which have not been started yet do not have an ESB page
mapped in the Linux address space. This crashes the 'crash kexec'
sequence on sPAPR guests.
To fix, force the mapping of the ESB page when an interrupt is being
mapped in the Linux IRQ number space. This is done by setting the
initial state of the interrupt to OFF which is not necessarily the
case on PowerNV.
Fixes: 243e25112d06 ("powerpc/xive: Native exploitation of the XIVE interrupt controller")
Cc: stable@vger.kernel.org # v4.12+
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031063100.3864-1-clg@kaod.org
|
|
It's KUAP, not KAUP. Fix typo in INT_COMMON macro.
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191022060603.24101-1-ajd@linux.ibm.com
|
|
The FSF does not reside in "675 Mass Ave, Cambridge" anymore...
let's simply use proper SPDX identifiers instead.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Acked-by: Russell Currey <ruscur@russell.cc>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190828060737.32531-1-thuth@redhat.com
|
|
Avoids confusion when printing Oops message like below
Faulting instruction address: 0xc00000000008bdb4
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Radix MMU=Hash SMP NR_CPUS=2048 NUMA PowerNV
This was because we never clear the MMU_FTR_HPTE_TABLE feature flag
even if we run with radix translation. It was discussed that we should
look at this feature flag as an indication of the capability to run
hash translation and we should not clear the flag even if we run in
radix translation. All the code paths check for radix_enabled() check and
if found true consider we are running with radix translation. Follow the
same sequence for finding the MMU translation string to be used in Oops
message.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190711145814.17970-1-aneesh.kumar@linux.ibm.com
|
|
arch/powerpc/platforms/cell/spufs/inode.c:201:22:
warning: variable ctx set but not used [-Wunused-but-set-variable]
It is not used since commit 67cba9fd6456 ("move
spu_forget() into spufs_rmdir()")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191023134423.15052-1-yuehaibing@huawei.com
|
|
The callback function of call_rcu() just calls a kfree(), so we
can use kfree_rcu() instead of call_rcu() + callback function.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190711141818.18044-1-yuehaibing@huawei.com
|
|
Fix sparse warnings:
arch/powerpc/platforms/powernv/opal-psr.c:20:1:
warning: symbol 'psr_mutex' was not declared. Should it be static?
arch/powerpc/platforms/powernv/opal-psr.c:27:3:
warning: symbol 'psr_attrs' was not declared. Should it be static?
arch/powerpc/platforms/powernv/opal-powercap.c:20:1:
warning: symbol 'powercap_mutex' was not declared. Should it be static?
arch/powerpc/platforms/powernv/opal-sensor-groups.c:20:1:
warning: symbol 'sg_mutex' was not declared. Should it be static?
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190702131733.44100-1-yuehaibing@huawei.com
|
|
CONFIG_INET6_XFRM_MODE_*
These Kconfig options has been removed in commit 4c145dce2601 ("xfrm:
make xfrm modes builtin") So there is no point to keep it in
defconfigs any longer.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
[mpe: Extract from cross arch patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190612071901.21736-1-yuehaibing@huawei.com
|
|
Remove .owner field if calls are used which set it automatically
Generated by: scripts/coccinelle/api/platform_no_drv_owner.cocci
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190218133950.95225-1-yuehaibing@huawei.com
|
|
There is no need to have the 'struct dentry *vpa_dir' variable static
since new value always be assigned before use it.
Fixes: c6c26fb55e8e ("powerpc/pseries: Export raw per-CPU VPA data via debugfs")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190218125644.87448-1-yuehaibing@huawei.com
|
|
Use DEFINE_DEBUGFS_ATTRIBUTE rather than DEFINE_SIMPLE_ATTRIBUTE
for debugfs files.
Semantic patch information:
Rationale: DEFINE_SIMPLE_ATTRIBUTE + debugfs_create_file()
imposes some significant overhead as compared to
DEFINE_DEBUGFS_ATTRIBUTE + debugfs_create_file_unsafe().
Generated by: scripts/coccinelle/api/debugfs/debugfs_simple_attr.cocci
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1545705876-63132-1-git-send-email-yuehaibing@huawei.com
|
|
Use DEFINE_DEBUGFS_ATTRIBUTE rather than DEFINE_SIMPLE_ATTRIBUTE
for debugfs files.
Semantic patch information:
Rationale: DEFINE_SIMPLE_ATTRIBUTE + debugfs_create_file()
imposes some significant overhead as compared to
DEFINE_DEBUGFS_ATTRIBUTE + debugfs_create_file_unsafe().
Generated by: scripts/coccinelle/api/debugfs/debugfs_simple_attr.cocci
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1543498518-107601-1-git-send-email-yuehaibing@huawei.com
|
|
rtas_parse_epow_errlog() should pass 'modifier' to
handle_system_shutdown, because event modifier only use
bottom 4 bits.
Reviewed-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191023134838.21280-1-yuehaibing@huawei.com
|
|
On powerpc, watchpoint match range is double-word granular. On a
watchpoint hit, DAR is set to the first byte of overlap between actual
access and watched range. And thus it's quite possible that DAR does
not point inside user specified range. Ex, say user creates a
watchpoint with address range 0x1004 to 0x1007. So hw would be
configured to watch from 0x1000 to 0x1007. If there is a 4 byte access
from 0x1002 to 0x1005, DAR will point to 0x1002 and thus interrupt
handler considers it as extraneous, but it's actually not, because
part of the access belongs to what user has asked.
Instead of blindly ignoring the exception, get actual address range by
analysing an instruction, and ignore only if actual range does not
overlap with user specified range.
Note: The behavior is unchanged for 8xx.
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191017093204.7511-5-ravi.bangoria@linux.ibm.com
|
|
ptrace_set_debugreg() does not consider new length while overwriting
the watchpoint. Fix that. ppc_set_hwdebug() aligns watchpoint address
to doubleword boundary but does not change the length. If address
range is crossing doubleword boundary and length is less then 8, we
will lose samples from second doubleword. So fix that as well.
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191017093204.7511-4-ravi.bangoria@linux.ibm.com
|
|
Watchpoint match range is always doubleword(8 bytes) aligned on
powerpc. If the given range is crossing doubleword boundary, we need
to increase the length such that next doubleword also get
covered. Ex,
address len = 6 bytes
|=========.
|------------v--|------v--------|
| | | | | | | | | | | | | | | | |
|---------------|---------------|
<---8 bytes--->
In such case, current code configures hw as:
start_addr = address & ~HW_BREAKPOINT_ALIGN
len = 8 bytes
And thus read/write in last 4 bytes of the given range is ignored.
Fix this by including next doubleword in the length.
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191017093204.7511-3-ravi.bangoria@linux.ibm.com
|
|
We are hadrcoding length everywhere in the watchpoint code. Introduce
macros for the length and use them.
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191017093204.7511-2-ravi.bangoria@linux.ibm.com
|
|
The issue was showing "Mitigation" message via sysfs whatever the
state of "RFI Flush", but it should show "Vulnerable" when it is
disabled.
If you have "L1D private" feature enabled and not "RFI Flush" you are
vulnerable to meltdown attacks.
"RFI Flush" is the key feature to mitigate the meltdown whatever the
"L1D private" state.
SEC_FTR_L1D_THREAD_PRIV is a feature for Power9 only.
So the message should be as the truth table shows:
CPU | L1D private | RFI Flush | sysfs
----|-------------|-----------|-------------------------------------
P9 | False | False | Vulnerable
P9 | False | True | Mitigation: RFI Flush
P9 | True | False | Vulnerable: L1D private per thread
P9 | True | True | Mitigation: RFI Flush, L1D private per thread
P8 | False | False | Vulnerable
P8 | False | True | Mitigation: RFI Flush
Output before this fix:
# cat /sys/devices/system/cpu/vulnerabilities/meltdown
Mitigation: RFI Flush, L1D private per thread
# echo 0 > /sys/kernel/debug/powerpc/rfi_flush
# cat /sys/devices/system/cpu/vulnerabilities/meltdown
Mitigation: L1D private per thread
Output after fix:
# cat /sys/devices/system/cpu/vulnerabilities/meltdown
Mitigation: RFI Flush, L1D private per thread
# echo 0 > /sys/kernel/debug/powerpc/rfi_flush
# cat /sys/devices/system/cpu/vulnerabilities/meltdown
Vulnerable: L1D private per thread
Signed-off-by: Gustavo L. F. Walbon <gwalbon@linux.ibm.com>
Signed-off-by: Mauro S. M. Rodrigues <maurosr@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190502210907.42375-1-gwalbon@linux.ibm.com
|
|
The stress test for vpmsum implementations executes a long for loop in
the kernel. This blocks the scheduler, which prevents other tasks from
running, resulting in a warning.
This fix adds a call to cond_reshed() at the end of each loop, which
allows the scheduler to run other tasks as required.
Signed-off-by: Chris Smart <chris.smart@humanservices.gov.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191103233356.5472-1-chris.smart@humanservices.gov.au
|
|
Let's allow to test the implementation without needing HW support.
When "simulate=1" is specified when loading the module, we bypass all
HW checks and HW calls. The sysfs file "simulate_loan_target_kb" can
be used to simulate HW requests.
The simualtion mode can be activated using:
modprobe cmm debug=1 simulate=1
And the requested loan target can be changed using:
echo X > /sys/devices/system/cmm/cmm0/simulate_loan_target_kb
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-11-david@redhat.com
|
|
balloon_page_alloc() will use GFP_HIGHUSER_MOVABLE in case we have
CONFIG_BALLOON_COMPACTION. This is now possible, as balloon pages are
movable with CONFIG_BALLOON_COMPACTION. Without
CONFIG_BALLOON_COMPACTION, GFP_HIGHUSER is used.
Note that apart from that, balloon_page_alloc() uses the following
flags:
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN
And current code used:
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC
GFP_HIGHUSER/GFP_HIGHUSER_MOVABLE include
__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL | __GFP_HIGHMEM
GFP_NOIO is __GFP_RECLAIM.
With CONFIG_BALLOON_COMPACTION, we essentially add:
__GFP_IO | __GFP_FS | __GFP_HARDWALL | __GFP_HIGHMEM | __GFP_MOVABLE
Without CONFIG_BALLOON_COMPACTION, we essentially add:
__GFP_IO | __GFP_FS | __GFP_HARDWALL | __GFP_HIGHMEM
I assume this is fine, as this is what all other balloon compaction
users use. If it turns out to be a problem, we could add __GFP_MOVABLE
manually if we have CONFIG_BALLOON_COMPACTION.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-10-david@redhat.com
|
|
We can now get rid of the cmm_lock and completely rely on the balloon
compaction internals, which now also manage the page list and the
lock.
Inflated/"loaned" pages are now movable. Memory blocks that contain
such pages can get offlined. Also, all such pages will be marked
PageOffline() and can therefore be excluded in memory dumps using
recent versions of makedumpfile.
Don't switch to balloon_page_alloc() yet (due to the GFP_NOIO). Will
do that separately to discuss this change in detail.
Signed-off-by: David Hildenbrand <david@redhat.com>
[mpe: Add isolated_pages-- in cmm_migratepage() as suggested by David]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-9-david@redhat.com
|
|
When switching to balloon compaction, we want to drop the cmm_lock and
completely rely on the balloon compaction list lock internally.
loaned_pages is currently protected under the cmm_lock.
Note: Right now cmm_alloc_pages() and cmm_free_pages() can be called
at the same time, e.g., via the thread and a concurrent OOM notifier.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-8-david@redhat.com
|
|
The memory isolate notifier was added to allow to offline memory
blocks that contain inflated/"loaned" pages. We can achieve the same
using the balloon compaction framework.
Get rid of the memory isolate notifier. Also, we can get rid of
cmm_mem_going_offline(), as we will never reach that code path now
when we have allocated memory in the balloon (allocated pages are
unmovable and will no longer be special-cased using the memory
isolation notifier).
Leave the memory notifier in place, so we can still back off in case
memory gets offlined.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-7-david@redhat.com
|
|
adjust_managed_page_count() performs a totalram_pages_add(), but also
adjusts the managed pages of the zone. Let's use that instead, similar
to virtio-balloon. Use it before freeing a page.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-6-david@redhat.com
|
|
We can simply store the pages in a list (page->lru), no need for a
separate data structure (+ complicated handling). This is how most
other balloon drivers store allocated pages without additional
tracking data.
For the notifiers, use page_to_pfn() to check if a page is in the
applicable range. Use page_to_phys() in plpar_page_set_loaned() and
plpar_page_set_active() (I assume due to the __pa() that's the right
thing to do).
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-5-david@redhat.com
|
|
No need to initialize rc. Also, let's return 0 directly when
succeeding.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-4-david@redhat.com
|
|
If we don't set the rc, we will return "0", making it look like we
succeeded.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-3-david@redhat.com
|
|
When unloading the module, one gets
------------[ cut here ]------------
Device 'cmm0' does not have a release() function, it is broken and must be fixed. See Documentation/kobject.txt.
WARNING: CPU: 0 PID: 19308 at drivers/base/core.c:1244 .device_release+0xcc/0xf0
...
We only have one static fake device. There is nothing to do when
releasing the device (via cmm_exit()).
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191031142933.10779-2-david@redhat.com
|
|
Advertise client support for the PAPR architected ibm,drc-info device
tree property during CAS handshake.
Fixes: c7a3275e0f9e ("powerpc/pseries: Revert support for ibm,drc-info devtree property")
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1573449697-5448-11-git-send-email-tyreld@linux.ibm.com
|
|
Older firmwares provided information about Dynamic Reconfig
Connectors (DRC) through several device tree properties, namely
ibm,drc-types, ibm,drc-indexes, ibm,drc-names, and
ibm,drc-power-domains. New firmwares have the ability to present this
same information in a much condensed format through a device tree
property called ibm,drc-info.
The existing cpu DLPAR hotplug code only understands the older DRC
property format when validating the drc-index of a cpu during a
hotplug add. This updates those code paths to use the ibm,drc-info
property, when present, instead for validation.
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1573449697-5448-4-git-send-email-tyreld@linux.ibm.com
|
|
There are a couple subtle errors in the mapping between cpu-ids and a
cpus associated drc-index when using the new ibm,drc-info property.
The first is that while drc-info may have been a supported firmware
feature at boot it is possible we have migrated to a CEC with older
firmware that doesn't support the ibm,drc-info property. In that case
the device tree would have been updated after migration to remove the
ibm,drc-info property and replace it with the older style ibm,drc-*
properties for types, indexes, names, and power-domains. PAPR even
goes as far as dictating that if we advertise support for drc-info
that we are capable of supporting either property type at runtime.
The second is that the first value of the ibm,drc-info property is
the int encoded count of drc-info entries. As such "value" returned
by of_prop_next_u32() is pointing at that count, and not the first
element of the first drc-info entry as is expected by the
of_read_drc_info_cell() helper.
Fix the first by ignoring DRC-INFO firmware feature and instead
testing directly for ibm,drc-info, and then falling back to the
old style ibm,drc-indexes in the case it doesn't exit.
Fix the second by incrementing value to the next element prior to
parsing drc-info entries.
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1573449697-5448-3-git-send-email-tyreld@linux.ibm.com
|
