On Fri, Mar 16, 2018 at 02:12:21PM -0700, Andrew Morton wrote:
> On Fri, 16 Mar 2018 15:14:08 -0400 jgli...@redhat.com wrote:
>
> > The hmm_mirror_register() function registers a callback for when
> > the CPU pagetable is modified. Normally, the device driver will
> > call hmm_mirror_unregister()
On Fri, Mar 16, 2018 at 1:56 PM, Kirill A. Shutemov
wrote:
>
> Increase of readahead window was proposed several times. And rejected.
> IIRC, Linus was against it.
I have never seen any valid situation that wasn't tuning for one odd
machine, usually with a horribly crappy disk setup and very
The ucd9000 series chips have gpio pins. Add a gpio chip interface to the ucd
device so that users can query and set the state of the gpio pins.
Add a debugfs interface using the existing pmbus debugfs directory to provide
MFR_STATUS and the status of the gpi faults to users.
Changes since v6:
The ucd9000 series chips have gpio pins. Add a gpio chip interface to the ucd
device so that users can query and set the state of the gpio pins.
Add a debugfs interface using the existing pmbus debugfs directory to provide
MFR_STATUS and the status of the gpi faults to users.
Changes since v6:
From: Christopher Bostic
Add a struct gpio_chip and define some methods so that this device's
I/O can be accessed via /sys/class/gpio.
Signed-off-by: Christopher Bostic
Signed-off-by: Andrew Jeffery
Signed-off-by: Eddie
From: Christopher Bostic
Expose the gpiN_fault fields of mfr_status as individual debugfs
attributes. This provides a way for users to be easily notified of gpi
faults. Also provide the whole mfr_status register in debugfs.
Signed-off-by: Christopher Bostic
From: Christopher Bostic
Add a struct gpio_chip and define some methods so that this device's
I/O can be accessed via /sys/class/gpio.
Signed-off-by: Christopher Bostic
Signed-off-by: Andrew Jeffery
Signed-off-by: Eddie James
---
drivers/hwmon/pmbus/ucd9000.c | 212
From: Christopher Bostic
Expose the gpiN_fault fields of mfr_status as individual debugfs
attributes. This provides a way for users to be easily notified of gpi
faults. Also provide the whole mfr_status register in debugfs.
Signed-off-by: Christopher Bostic
Signed-off-by: Andrew Jeffery
On Fri, Mar 16, 2018 at 02:09:59PM -0700, Andrew Morton wrote:
> On Fri, 16 Mar 2018 15:14:07 -0400 jgli...@redhat.com wrote:
>
> > From: Jérôme Glisse
> >
> > The #if/#else/#endif for IS_ENABLED(CONFIG_HMM) were wrong.
>
> "were wrong" is not a sufficient explanation of
On Fri, Mar 16, 2018 at 02:09:59PM -0700, Andrew Morton wrote:
> On Fri, 16 Mar 2018 15:14:07 -0400 jgli...@redhat.com wrote:
>
> > From: Jérôme Glisse
> >
> > The #if/#else/#endif for IS_ENABLED(CONFIG_HMM) were wrong.
>
> "were wrong" is not a sufficient explanation of the problem,
> I agree, let's not have you run into circles, let's just use your
> patches as they are since they fix the problem and are not intrusive in
> any way.
Agreed, this is too complex, for little gain.
Andrew
> I agree, let's not have you run into circles, let's just use your
> patches as they are since they fix the problem and are not intrusive in
> any way.
Agreed, this is too complex, for little gain.
Andrew
On Fri, 16 Mar 2018 15:14:08 -0400 jgli...@redhat.com wrote:
> The hmm_mirror_register() function registers a callback for when
> the CPU pagetable is modified. Normally, the device driver will
> call hmm_mirror_unregister() when the process using the device is
> finished. However, if the process
On Fri, 16 Mar 2018 15:14:08 -0400 jgli...@redhat.com wrote:
> The hmm_mirror_register() function registers a callback for when
> the CPU pagetable is modified. Normally, the device driver will
> call hmm_mirror_unregister() when the process using the device is
> finished. However, if the process
There are three significant concerns about the cgroup aware oom killer as
it is implemented in -mm:
(1) allows users to evade the oom killer by creating subcontainers or
using other controllers since scoring is done per cgroup and not
hierarchically,
(2) unfairly compares the root
There are three significant concerns about the cgroup aware oom killer as
it is implemented in -mm:
(1) allows users to evade the oom killer by creating subcontainers or
using other controllers since scoring is done per cgroup and not
hierarchically,
(2) unfairly compares the root
On 03/16/2018 01:13 PM, Grygorii Strashko wrote:
>
>
> On 03/16/2018 02:54 PM, Andrew Lunn wrote:
>>> The phydrv->mdiodrv.flags can be accessible only after call to
>>> of_phy_connect()/phy_connect(),
>>
>> You need to use a function like of_phy_find_device() to get the
>> phydev, set the flag,
Now that each mem cgroup on the system has a memory.oom_policy tunable to
specify oom kill selection behavior, remove the needless "groupoom" mount
option that requires (1) the entire system to be forced, perhaps
unnecessarily, perhaps unexpectedly, into a single oom policy that
differs from the
On 03/16/2018 01:13 PM, Grygorii Strashko wrote:
>
>
> On 03/16/2018 02:54 PM, Andrew Lunn wrote:
>>> The phydrv->mdiodrv.flags can be accessible only after call to
>>> of_phy_connect()/phy_connect(),
>>
>> You need to use a function like of_phy_find_device() to get the
>> phydev, set the flag,
Now that each mem cgroup on the system has a memory.oom_policy tunable to
specify oom kill selection behavior, remove the needless "groupoom" mount
option that requires (1) the entire system to be forced, perhaps
unnecessarily, perhaps unexpectedly, into a single oom policy that
differs from the
On Fri, 16 Mar 2018 15:14:07 -0400 jgli...@redhat.com wrote:
> From: Jérôme Glisse
>
> The #if/#else/#endif for IS_ENABLED(CONFIG_HMM) were wrong.
"were wrong" is not a sufficient explanation of the problem, especially
if we're requesting a -stable backport. Please fully
On Fri, 16 Mar 2018 15:14:07 -0400 jgli...@redhat.com wrote:
> From: Jérôme Glisse
>
> The #if/#else/#endif for IS_ENABLED(CONFIG_HMM) were wrong.
"were wrong" is not a sufficient explanation of the problem, especially
if we're requesting a -stable backport. Please fully describe the
effects
With the current implementation of the cgroup-aware oom killer,
memory.oom_group defines two behaviors:
- consider the footprint of the "group" consisting of the mem cgroup
itself and all descendants for comparison with other cgroups, and
- when selected as the victim mem cgroup, kill all
With the current implementation of the cgroup-aware oom killer,
memory.oom_group defines two behaviors:
- consider the footprint of the "group" consisting of the mem cgroup
itself and all descendants for comparison with other cgroups, and
- when selected as the victim mem cgroup, kill all
There are several downsides to the current implementation that compares
the root mem cgroup with leaf mem cgroups for the cgroup-aware oom killer.
For example, /proc/pid/oom_score_adj is accounted for processes attached
to the root mem cgroup but not leaves. This leads to wild inconsistencies
One of the three significant concerns brought up about the cgroup aware
oom killer is that its decisionmaking is completely evaded by creating
subcontainers and attaching processes such that the ancestor's usage does
not exceed another cgroup on the system.
Consider the example from the previous
The cgroup aware oom killer is needlessly enforced for the entire system
by a mount option. It's unnecessary to force the system into a single
oom policy: either cgroup aware, or the traditional process aware.
This patch introduces a memory.oom_policy tunable for all mem cgroups.
It is currently
One of the three significant concerns brought up about the cgroup aware
oom killer is that its decisionmaking is completely evaded by creating
subcontainers and attaching processes such that the ancestor's usage does
not exceed another cgroup on the system.
Consider the example from the previous
The cgroup aware oom killer is needlessly enforced for the entire system
by a mount option. It's unnecessary to force the system into a single
oom policy: either cgroup aware, or the traditional process aware.
This patch introduces a memory.oom_policy tunable for all mem cgroups.
It is currently
There are several downsides to the current implementation that compares
the root mem cgroup with leaf mem cgroups for the cgroup-aware oom killer.
For example, /proc/pid/oom_score_adj is accounted for processes attached
to the root mem cgroup but not leaves. This leads to wild inconsistencies
The cgroup-aware oom killer currently considers the set of allowed nodes
for the allocation that triggers the oom killer and discounts usage from
disallowed nodes when comparing cgroups.
If a cgroup has both the cpuset and memory controllers enabled, it may be
possible to restrict allocations to
The cgroup-aware oom killer currently considers the set of allowed nodes
for the allocation that triggers the oom killer and discounts usage from
disallowed nodes when comparing cgroups.
If a cgroup has both the cpuset and memory controllers enabled, it may be
possible to restrict allocations to
Dave Hansen writes:
> On 03/16/2018 01:06 PM, Eric W. Biederman wrote:
>>> It does not revert cleanly so I reverted it manually. Patch doing that
>>> is attached. Should we do this, or is there a better option?
>> Please see:
>> 859d880cf544 ("signal: Correct the offset
Dave Hansen writes:
> On 03/16/2018 01:06 PM, Eric W. Biederman wrote:
>>> It does not revert cleanly so I reverted it manually. Patch doing that
>>> is attached. Should we do this, or is there a better option?
>> Please see:
>> 859d880cf544 ("signal: Correct the offset of si_pkey in struct
shmem_unused_huge_shrink() gets called from reclaim path. Waiting for page
lock may lead to deadlock there.
There was a bug report that may be attributed to this:
http://lkml.kernel.org/r/alpine.lrh.2.11.1801242349220.30...@mail.ewheeler.net
Replace lock_page() with trylock_page() and skip the
shmem_unused_huge_shrink() gets called from reclaim path. Waiting for page
lock may lead to deadlock there.
There was a bug report that may be attributed to this:
http://lkml.kernel.org/r/alpine.lrh.2.11.1801242349220.30...@mail.ewheeler.net
Replace lock_page() with trylock_page() and skip the
These macros are similar to the DRM_ with the addition
of a struct device * to the arguments.
Convert the single drm_dev_printk function into 2 separate functions.
drm_dev_printk with a KERN_ * for generic use and drm_dev_dbg
for conditional masked use.
Remove the __func__ argument and use
These macros are similar to the DRM_ with the addition
of a struct device * to the arguments.
Convert the single drm_dev_printk function into 2 separate functions.
drm_dev_printk with a KERN_ * for generic use and drm_dev_dbg
for conditional masked use.
Remove the __func__ argument and use
On Fri, Mar 16, 2018 at 11:25:08AM -0700, Wei Wang wrote:
> From: Wei Wang
>
> Change VM_MAX_READAHEAD value from the default 128KB to a configurable
> value. This will allow the readahead window to grow to a maximum size
> bigger than 128KB during boot, which could benefit to
On Fri, Mar 16, 2018 at 11:25:08AM -0700, Wei Wang wrote:
> From: Wei Wang
>
> Change VM_MAX_READAHEAD value from the default 128KB to a configurable
> value. This will allow the readahead window to grow to a maximum size
> bigger than 128KB during boot, which could benefit to sequential read
>
On Fri, Mar 2, 2018 at 9:10 AM, Joerg Roedel wrote:
> On Thu, Mar 01, 2018 at 10:38:21AM -0800, Linus Torvalds wrote:
>> Note that debug traps can happen regardless of TF, Think kgdb etc.
>> Arguably kgdb users get what they deserve, but still.. I think root
>> can set kernel
On Fri, Mar 2, 2018 at 9:10 AM, Joerg Roedel wrote:
> On Thu, Mar 01, 2018 at 10:38:21AM -0800, Linus Torvalds wrote:
>> Note that debug traps can happen regardless of TF, Think kgdb etc.
>> Arguably kgdb users get what they deserve, but still.. I think root
>> can set kernel breakpoints too.
>
>
Hi Martin,
On Fri, Mar 16, 2018 at 11:54:30AM -0400, Martin K. Petersen wrote:
>
> Sudip,
>
> > While whitelisting Micron M500DC drives, the tweaked blacklist entry
> > enabled queued TRIM from M500IT variants also. But these do not support
> > queued TRIM. And while using those SSDs with the
Hi Martin,
On Fri, Mar 16, 2018 at 11:54:30AM -0400, Martin K. Petersen wrote:
>
> Sudip,
>
> > While whitelisting Micron M500DC drives, the tweaked blacklist entry
> > enabled queued TRIM from M500IT variants also. But these do not support
> > queued TRIM. And while using those SSDs with the
On Fri, Mar 16, 2018 at 03:04:47PM -0500, Eddie James wrote:
>
>
> On 03/16/2018 02:59 PM, Guenter Roeck wrote:
> >On Fri, Mar 16, 2018 at 02:25:59PM -0500, Eddie James wrote:
> >>From: Christopher Bostic
> >>
> >>Expose the gpiN_fault fields of mfr_status as
On Fri, Mar 16, 2018 at 03:04:47PM -0500, Eddie James wrote:
>
>
> On 03/16/2018 02:59 PM, Guenter Roeck wrote:
> >On Fri, Mar 16, 2018 at 02:25:59PM -0500, Eddie James wrote:
> >>From: Christopher Bostic
> >>
> >>Expose the gpiN_fault fields of mfr_status as individual debugfs
> >>attributes.
On Fri, Mar 16, 2018 at 06:49:08PM +, Wei Wang wrote:
> Android devices boot time benefits by bigger readahead window setting from
> init. This patch will make readahead window a config so early boot can
> benefit by it as well.
Why not put that in the changelog text?
On Fri, Mar 16, 2018 at 06:49:08PM +, Wei Wang wrote:
> Android devices boot time benefits by bigger readahead window setting from
> init. This patch will make readahead window a config so early boot can
> benefit by it as well.
Why not put that in the changelog text?
Le 16/03/2018 à 20:27, David Miller a écrit :
From: Christophe JAILLET
Date: Wed, 14 Mar 2018 22:09:34 +0100
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c
b/drivers/net/ethernet/arc/emac_rockchip.c
index 16f9bee992fe..8ee9dfd0e363 100644
---
Le 16/03/2018 à 20:27, David Miller a écrit :
From: Christophe JAILLET
Date: Wed, 14 Mar 2018 22:09:34 +0100
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c
b/drivers/net/ethernet/arc/emac_rockchip.c
index 16f9bee992fe..8ee9dfd0e363 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
Le 16/03/2018 à 20:27, David Miller a écrit :
From: Christophe JAILLET
Date: Wed, 14 Mar 2018 22:09:34 +0100
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c
b/drivers/net/ethernet/arc/emac_rockchip.c
index 16f9bee992fe..8ee9dfd0e363 100644
---
Le 16/03/2018 à 20:27, David Miller a écrit :
From: Christophe JAILLET
Date: Wed, 14 Mar 2018 22:09:34 +0100
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c
b/drivers/net/ethernet/arc/emac_rockchip.c
index 16f9bee992fe..8ee9dfd0e363 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
On Thu, Mar 15, 2018 at 04:56:21PM -0700, Dmitry Torokhov wrote:
> On Wed, Mar 14, 2018 at 08:51:24PM +, Nick Dyer wrote:
> > On Mon, Mar 12, 2018 at 12:08:54PM -0700, Dmitry Torokhov wrote:
> > > The way we are supposed to put controller to sleep and wake it up does not
> > > depend on the
On Thu, Mar 15, 2018 at 04:56:21PM -0700, Dmitry Torokhov wrote:
> On Wed, Mar 14, 2018 at 08:51:24PM +, Nick Dyer wrote:
> > On Mon, Mar 12, 2018 at 12:08:54PM -0700, Dmitry Torokhov wrote:
> > > The way we are supposed to put controller to sleep and wake it up does not
> > > depend on the
On Thu, Mar 15, 2018 at 05:06:14PM -0700, Dmitry Torokhov wrote:
> On Wed, Mar 14, 2018 at 08:59:38PM +, Nick Dyer wrote:
> > On Mon, Mar 12, 2018 at 12:09:07PM -0700, Dmitry Torokhov wrote:
> > > - /*
> > > - * Ignore ACPI devices representing bootloader mode.
> > > - *
> > > - * This is a
On Thu, Mar 15, 2018 at 05:06:14PM -0700, Dmitry Torokhov wrote:
> On Wed, Mar 14, 2018 at 08:59:38PM +, Nick Dyer wrote:
> > On Mon, Mar 12, 2018 at 12:09:07PM -0700, Dmitry Torokhov wrote:
> > > - /*
> > > - * Ignore ACPI devices representing bootloader mode.
> > > - *
> > > - * This is a
This is the code needed by IMA-appraise to work with modsig signatures.
It will be used by the next two patches.
Signed-off-by: Thiago Jung Bauermann
---
security/integrity/ima/Kconfig | 3 +
security/integrity/ima/ima.h| 41
This is the code needed by IMA-appraise to work with modsig signatures.
It will be used by the next two patches.
Signed-off-by: Thiago Jung Bauermann
---
security/integrity/ima/Kconfig | 3 +
security/integrity/ima/ima.h| 41
security/integrity/ima/ima_modsig.c | 181
Hello,
The main highlight in this version is that it's not necessary to appraise
the file before storing its measurement anymore. This is possible due to a
new approach that Mimi suggested: we decide whether the modsig should be
used or not at the time it is read from the file, while before we
Hello,
The main highlight in this version is that it's not necessary to appraise
the file before storing its measurement anymore. This is possible due to a
new approach that Mimi suggested: we decide whether the modsig should be
used or not at the time it is read from the file, while before we
IMA will need to access the digest of the PKCS7 message (as calculated by
the kernel) before the signature is verified, so introduce
pkcs7_get_digest() for that purpose.
Also, modify pkcs7_digest() to detect when the digest was already
calculated so that it doesn't have to do redundant work.
IMA will need to access the digest of the PKCS7 message (as calculated by
the kernel) before the signature is verified, so introduce
pkcs7_get_digest() for that purpose.
Also, modify pkcs7_digest() to detect when the digest was already
calculated so that it doesn't have to do redundant work.
This avoids a dependency cycle in CONFIG_IMA_APPRAISE_MODSIG (introduced by
a later patch in this series): it will select CONFIG_MODULE_SIG_FORMAT
which in turn selects CONFIG_KEYS. Kconfig then complains that
CONFIG_INTEGRITY_SIGNATURE depends on CONFIG_KEYS.
Signed-off-by: Thiago Jung Bauermann
This avoids a dependency cycle in CONFIG_IMA_APPRAISE_MODSIG (introduced by
a later patch in this series): it will select CONFIG_MODULE_SIG_FORMAT
which in turn selects CONFIG_KEYS. Kconfig then complains that
CONFIG_INTEGRITY_SIGNATURE depends on CONFIG_KEYS.
Signed-off-by: Thiago Jung Bauermann
IMA will need to obtain the keyring used to verify file signatures so that
it can verify the module-style signature appended to files.
Signed-off-by: Thiago Jung Bauermann
---
security/integrity/digsig.c| 28 +---
IMA will need to obtain the keyring used to verify file signatures so that
it can verify the module-style signature appended to files.
Signed-off-by: Thiago Jung Bauermann
---
security/integrity/digsig.c| 28 +---
security/integrity/integrity.h | 6 ++
2 files
This patch introduces the modsig keyword to the IMA policy syntax to
specify that a given hook should expect the file to have the IMA signature
appended to it. Here is how it can be used in a rule:
appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig
With this rule, IMA will accept
This patch introduces the modsig keyword to the IMA policy syntax to
specify that a given hook should expect the file to have the IMA signature
appended to it. Here is how it can be used in a rule:
appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig
With this rule, IMA will accept
IMA will only look for a modsig if the xattr sig references a key which is
not in the expected kernel keyring. To that end, introduce
asymmetric_sig_has_known_key().
The logic of extracting the key used in the xattr sig is factored out from
asymmetric_verify() so that it can be used by the new
IMA will only look for a modsig if the xattr sig references a key which is
not in the expected kernel keyring. To that end, introduce
asymmetric_sig_has_known_key().
The logic of extracting the key used in the xattr sig is factored out from
asymmetric_verify() so that it can be used by the new
This patch actually implements the appraise_type=imasig|modsig option,
allowing IMA to read and verify modsig signatures.
In case both are present in the same file, IMA will first check whether the
key used by the xattr signature is present in the kernel keyring. If not,
it will try the appended
This patch actually implements the appraise_type=imasig|modsig option,
allowing IMA to read and verify modsig signatures.
In case both are present in the same file, IMA will first check whether the
key used by the xattr signature is present in the kernel keyring. If not,
it will try the appended
Define new "d-sig" template field which holds the digest that is expected
to match the one contained in the modsig.
Also add modsig support to the "sig" template field, allowing the the
contents of the modsig to be included in the measurement list.
Suggested-by: Mimi Zohar
Define new "d-sig" template field which holds the digest that is expected
to match the one contained in the modsig.
Also add modsig support to the "sig" template field, allowing the the
contents of the modsig to be included in the measurement list.
Suggested-by: Mimi Zohar
Signed-off-by: Thiago
ima_read_modsig() will need it so that it can show an error message.
Signed-off-by: Thiago Jung Bauermann
---
security/integrity/ima/ima.h| 2 ++
security/integrity/ima/ima_policy.c | 12 ++--
2 files changed, 8 insertions(+), 6 deletions(-)
diff
ima_read_modsig() will need it so that it can show an error message.
Signed-off-by: Thiago Jung Bauermann
---
security/integrity/ima/ima.h| 2 ++
security/integrity/ima/ima_policy.c | 12 ++--
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git
IMA will need to know the key that signed a given PKCS#7 message, so add
pkcs7_get_message_sig().
It will also need to verify an already parsed PKCS#7 message. For this
purpose, add verify_pkcs7_message_sig() which takes a struct pkcs7_message
for verification instead of the raw bytes that
With the introduction of another IMA signature type (modsig), some places
will need to check for both of them. It is cleaner to do that if there's a
helper function to tell whether an xattr_value represents an IMA
signature.
Suggested-by: Mimi Zohar
Signed-off-by:
With the introduction of another IMA signature type (modsig), some places
will need to check for both of them. It is cleaner to do that if there's a
helper function to tell whether an xattr_value represents an IMA
signature.
Suggested-by: Mimi Zohar
Signed-off-by: Thiago Jung Bauermann
---
IMA will need to know the key that signed a given PKCS#7 message, so add
pkcs7_get_message_sig().
It will also need to verify an already parsed PKCS#7 message. For this
purpose, add verify_pkcs7_message_sig() which takes a struct pkcs7_message
for verification instead of the raw bytes that
IMA will use the module_signature format for append signatures, so export
the relevant definitions and factor out the code which verifies that the
appended signature trailer is valid.
Also, create a CONFIG_MODULE_SIG_FORMAT option so that IMA can select it
and be able to use validate_module_sig()
IMA will use the module_signature format for append signatures, so export
the relevant definitions and factor out the code which verifies that the
appended signature trailer is valid.
Also, create a CONFIG_MODULE_SIG_FORMAT option so that IMA can select it
and be able to use validate_module_sig()
The vmx module parameters are supposed to be unsigned variants.
Also fixed the checkpatch errors like the one below.
WARNING: Symbolic permissions 'S_IRUGO' are not preferred. Consider using octal
permissions '0444'.
+module_param(ple_gap, uint, S_IRUGO);
Signed-off-by: Babu Moger
The vmx module parameters are supposed to be unsigned variants.
Also fixed the checkpatch errors like the one below.
WARNING: Symbolic permissions 'S_IRUGO' are not preferred. Consider using octal
permissions '0444'.
+module_param(ple_gap, uint, S_IRUGO);
Signed-off-by: Babu Moger
---
This patch adds the support for pause filtering threshold. This feature
support is indicated by CPUID Fn8000_000A_EDX. See AMD APM Vol 2 Section
15.14.4 Pause Intercept Filtering for more details.
In this mode, a 16-bit pause filter threshold field is added in VMCB.
The threshold value is a cycle
This series adds PLE(pause loop exit) logic from VMX to SVM.
We have noticed considerable reduction in number of VMEXITS due to pause
interceptions after these changes. Here are the numbers on one guest with
32 vcpus on AMD EPYC system. We have used boot parameter idle=poll to
simulate extensive
This patch brings some of the code from vmx to x86.h header file. Now, we
can share this code between vmx and svm. Modified couple functions to make
it common.
Signed-off-by: Babu Moger
---
arch/x86/kvm/vmx.c | 48 +---
This patch adds the support for pause filtering threshold. This feature
support is indicated by CPUID Fn8000_000A_EDX. See AMD APM Vol 2 Section
15.14.4 Pause Intercept Filtering for more details.
In this mode, a 16-bit pause filter threshold field is added in VMCB.
The threshold value is a cycle
This series adds PLE(pause loop exit) logic from VMX to SVM.
We have noticed considerable reduction in number of VMEXITS due to pause
interceptions after these changes. Here are the numbers on one guest with
32 vcpus on AMD EPYC system. We have used boot parameter idle=poll to
simulate extensive
This patch brings some of the code from vmx to x86.h header file. Now, we
can share this code between vmx and svm. Modified couple functions to make
it common.
Signed-off-by: Babu Moger
---
arch/x86/kvm/vmx.c | 48 +---
arch/x86/kvm/x86.h | 35
Bring the PLE(pause loop exit) logic to AMD svm driver.
While testing, we found this helping in situations where numerous
pauses are generated. Without these patches we could see continuos
VMEXITS due to pause interceptions. Tested it on AMD EPYC server with
boot parameter idle=poll on a VM with
Bring the PLE(pause loop exit) logic to AMD svm driver.
While testing, we found this helping in situations where numerous
pauses are generated. Without these patches we could see continuos
VMEXITS due to pause interceptions. Tested it on AMD EPYC server with
boot parameter idle=poll on a VM with
Get rid of ple_window_actual_max, because its benefits are really
minuscule and the logic is complicated.
The overflows(and underflow) are controlled in __ple_window_grow
and _ple_window_shrink respectively.
Suggested-by: Radim Krčmář
Signed-off-by: Babu Moger
Get rid of ple_window_actual_max, because its benefits are really
minuscule and the logic is complicated.
The overflows(and underflow) are controlled in __ple_window_grow
and _ple_window_shrink respectively.
Suggested-by: Radim Krčmář
Signed-off-by: Babu Moger
---
arch/x86/kvm/vmx.c | 22
Quoting sean.w...@mediatek.com (2018-02-17 11:54:36)
> From: Sean Wang
>
> All ethsys, pciesys and ssusbsys internally include reset controller, so
> explicitly add back these missing cell definitions to related bindings
> and examples.
>
> Signed-off-by: Sean Wang
From: Jérôme Glisse
Move hmm_pfns_clear() closer to where it is use to make it clear it
is not use by page table walkers.
Signed-off-by: Jérôme Glisse
Cc: Evgeny Baskakov
Cc: Ralph Campbell
Cc: Mark Hairgrove
Quoting sean.w...@mediatek.com (2018-02-17 11:54:36)
> From: Sean Wang
>
> All ethsys, pciesys and ssusbsys internally include reset controller, so
> explicitly add back these missing cell definitions to related bindings
> and examples.
>
> Signed-off-by: Sean Wang
> Cc: Rob Herring
> Cc:
From: Jérôme Glisse
Move hmm_pfns_clear() closer to where it is use to make it clear it
is not use by page table walkers.
Signed-off-by: Jérôme Glisse
Cc: Evgeny Baskakov
Cc: Ralph Campbell
Cc: Mark Hairgrove
Cc: John Hubbard
---
mm/hmm.c | 16
1 file changed, 8
From: Jérôme Glisse
Make naming consistent accross code, DEVICE_PRIVATE is the name use
outside HMM code so use that one.
Signed-off-by: Jérôme Glisse
Cc: Evgeny Baskakov
Cc: Ralph Campbell
Cc: Mark Hairgrove
From: Jérôme Glisse
This change hmm_vma_fault() to not take a global write fault flag
for a range but instead rely on caller to populate HMM pfns array
with proper fault flag ie HMM_PFN_VALID if driver want read fault
for that address or HMM_PFN_VALID and HMM_PFN_WRITE for
301 - 400 of 2832 matches
Mail list logo